# Diogenes Autonomous Microservice Gateway (remote · diogenes-micro-gateway.corinth.workers.dev)

Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `diogenes-micro-gateway.corinth.workers.dev`: 61/100 (this document), [markdown](https://verifymcp.io/servers/stand-out-of-my-sun-diogenes-gateway/diogenes-micro-gateway.md), [page](https://verifymcp.io/servers/stand-out-of-my-sun-diogenes-gateway/diogenes-micro-gateway)

## Channel facts

- Endpoint: `https://diogenes-micro-gateway.corinth.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 13455 tokens (~189/item across 71 items; 71 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 4 days we've observed: 15 tool removals, 0 breaking changes, 0 auth/transport breaks, 71 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_python_sandbox" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 71 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Diogenes Autonomous Microservice Gateway MCP server?

Diogenes Autonomous Microservice Gateway is a hosted endpoint at https://diogenes-micro-gateway.corinth.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http stand-out-of-my-sun-diogenes-gateway 'https://diogenes-micro-gateway.corinth.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "stand-out-of-my-sun-diogenes-gateway": {
      "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "stand-out-of-my-sun-diogenes-gateway": {
      "type": "http",
      "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.stand-out-of-my-sun-diogenes-gateway]
url = "https://diogenes-micro-gateway.corinth.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "stand-out-of-my-sun-diogenes-gateway": {
      "type": "remote",
      "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add stand-out-of-my-sun-diogenes-gateway --url 'https://diogenes-micro-gateway.corinth.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  stand-out-of-my-sun-diogenes-gateway:
    url: "https://diogenes-micro-gateway.corinth.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "stand-out-of-my-sun-diogenes-gateway": {
      "Transport": "http",
      "Url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add stand-out-of-my-sun-diogenes-gateway -t streamable-http -u 'https://diogenes-micro-gateway.corinth.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "stand-out-of-my-sun-diogenes-gateway": {
      "type": "http",
      "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 61, +2)

- [security regression] Stability: 0.07 → fail
- [security regression] A breaking change shipped without a version bump: still 2.5.0
- [security regression] Tool “guardrail_verify” was removed
- [security regression] Tool “agent_context_compaction_verifier” was removed
- [security regression] Tool “agent_hallucination_auditor” was removed
- [security regression] Tool “agent_loop_circuit_breaker” was removed
- [security regression] Tool “agent_mcp_manifest_auditor” was removed
- [security regression] Tool “agent_mcp_router” was removed
- [security regression] Tool “agent_prompt_compiler” was removed
- [security regression] Tool “agent_schema_enforcer” was removed
- [security regression] Tool “agent_sql_guard” was removed
- [security regression] Tool “ai_antigravity_agent” was removed
- [security regression] Tool “ai_audio_live” was removed
- [security regression] Tool “ai_code_gen” was removed
- [security regression] Tool “ai_computer_use” was removed
- [security regression] Tool “ai_deep_research” was removed
- [security regression] Tool “ai_embeddings” was removed
- [security regression] Tool “ai_extract” was removed
- [security regression] Tool “ai_generate” was removed
- [security regression] Tool “ai_grounded_maps” was removed
- [security regression] Tool “ai_grounded_search” was removed
- [security regression] Tool “ai_image_gen” was removed
- [security regression] Tool “ai_music_gen” was removed
- [security regression] Tool “ai_omni” was removed
- [security regression] Tool “ai_robotics” was removed
- [security regression] Tool “ai_summarize” was removed
- [security regression] Tool “ai_tts” was removed
- [security regression] Tool “ai_video_gen” was removed
- [security regression] Tool “clean_data” was removed
- [security regression] Tool “code_sandbox” was removed
- [security regression] Tool “contract_audit” was removed
- [security regression] Tool “crypto_address_poisoning_check” was removed
- [security regression] Tool “crypto_bridge_quote” was removed
- [security regression] Tool “crypto_eip712_permit_decoder” was removed
- [security regression] Tool “crypto_utxo_consolidation_planner” was removed
- [security regression] Tool “eve_gate_route_planner” was removed
- [security regression] Tool “eve_killmail_threat_intel” was removed
- [security regression] Tool “eve_move_assembly_coder” was removed
- [security regression] Tool “eve_network_node_gj_optimizer” was removed
- [security regression] Tool “eve_sovereignty_fuel_radar” was removed
- [security regression] Tool “eve_ssu_market_maker” was removed
- [security regression] Tool “eve_sui_ptb_simulator” was removed
- [security regression] Tool “eve_turret_target_matrix” was removed
- [security regression] Tool “eve_zklogin_character_verifier” was removed
- [security regression] Tool “http402_challenge_verifier” was removed
- [security regression] Tool “json_repair” was removed
- [security regression] Tool “mcp_rugpull_diff” was removed
- [security regression] Tool “mcp_sampling_guard” was removed
- [security regression] Tool “mempool_fee” was removed
- [security regression] Tool “mev_risk” was removed
- [security regression] Tool “mpp_agent_escrow_arbiter” was removed
- [security regression] Tool “mpp_deep_search” was removed
- [security regression] Tool “mpp_session_infer” was removed
- [security regression] Tool “regex_oracle” was removed
- [security regression] Tool “scrub_pii” was removed
- [security regression] Tool “solana_risk” was removed
- [security regression] Tool “swap_rate” was removed
- [security regression] Tool “tool_output_firewall” was removed
- [security regression] Tool “web_brief” was removed
- [security regression] Tool “x402_embeddings” was removed
- [security regression] Tool “x402_solana_priority_fee_oracle” was removed
- [security regression] Tool “x402_token_meta” was removed
- [security regression] Tool “x402_whale_radar” was removed
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 41% → 100%
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: fair → excellent
- [functional] Destructive annotations: pass → 0
- [functional] New tool “detect_agent_action_loop”
- [functional] New tool “detect_mcp_schema_rugpull”
- [functional] New tool “detect_openapi_breaking_changes”
- [functional] New tool “diff_agent_memory_checkpoint”
- [functional] New tool “enforce_json_schema_types”
- [functional] New tool “estimate_bitcoin_mempool_fees”
- [functional] New tool “estimate_solana_priority_fees”
- [functional] New tool “evaluate_ab_statistical_significance”
- [functional] New tool “evaluate_deterministic_math”
- [functional] New tool “evaluate_dex_mev_risk”
- [functional] New tool “evaluate_solana_token_risk”
- [functional] New tool “execute_antigravity_agent”
- [functional] New tool “execute_python_sandbox”
- [functional] New tool “extract_structured_json_entities”
- [functional] New tool “generate_boundary_test_vectors”
- [functional] New tool “generate_gemini_completion”
- [functional] New tool “generate_gemini_embeddings”
- [functional] New tool “generate_nano_banana_image”
- [functional] New tool “generate_veo_cinematic_video”
- [functional] New tool “generate_x402_vector_embeddings”
- [functional] New tool “heal_malformed_json”
- [functional] New tool “infer_mpp_streaming_session”
- [functional] New tool “inspect_solana_token_liquidity”
- [functional] New tool “isolate_stacktrace_root_cause”
- [functional] New tool “operate_computer_use_agent”
- [functional] New tool “plan_bitcoin_utxo_consolidation”
- [functional] New tool “plan_context_token_budget”
- [functional] New tool “plan_robotics_spatial_trajectory”
- [functional] New tool “process_live_audio_dialogue”
- [functional] New tool “prune_context_skeleton”
- [functional] New tool “redact_sensitive_pii”
- [functional] New tool “rerank_hybrid_rag_chunks”
- [functional] New tool “route_mcp_workflow_plan”
- [functional] New tool “sanitize_tool_output_stream”
- [functional] New tool “scan_solana_cpi_reentrancy”
- [functional] New tool “schedule_critical_path_tasks”
- [functional] New tool “search_gemini_grounded_maps”
- [functional] New tool “search_gemini_grounded_web”
- [functional] New tool “simulate_evm_transaction_calldata”
- [functional] New tool “simulate_monte_carlo_risk”
- [functional] New tool “summarize_technical_document”
- [functional] New tool “synthesize_gemini_speech_audio”
- [functional] New tool “synthesize_python_automation_code”
- [functional] New tool “synthesize_safe_regex”
- [functional] New tool “synthesize_web_intelligence_brief”
- [functional] New tool “track_solana_whale_flows”
- [functional] New tool “validate_mcp_sampling_request”
- [functional] New tool “validate_sql_query_ast”
- [functional] New tool “verify_a2a_agent_card”
- [functional] New tool “verify_agent_command_safety”
- [functional] New tool “verify_context_compaction_fidelity”
- [functional] New tool “verify_http402_payment_challenge”
- [functional] New tool “analyze_ast_symbol_graph”
- [functional] New tool “analyze_omni_multimodal_input”
- [functional] New tool “apply_fuzzy_code_patch”
- [functional] New tool “arbitrate_agent_deliverable_escrow”
- [functional] New tool “audit_mcp_server_manifest”
- [functional] New tool “audit_module_dependency_cycles”
- [functional] New tool “audit_outbound_egress_url”
- [functional] New tool “audit_response_factuality”
- [functional] New tool “audit_smart_contract_code”
- [functional] New tool “calculate_spot_swap_rate”
- [functional] New tool “clean_tabular_dataset”
- [functional] New tool “compare_crosschain_bridge_routes”
- [functional] New tool “compile_mpp_research_dossier”
- [functional] New tool “compile_polyglot_type_schemas”
- [functional] New tool “compile_xml_agent_prompt”
- [functional] New tool “compose_lyria_music_track”
- [functional] New tool “conduct_deep_research_investigation”
- [functional] New tool “decode_eip712_permit_signature”
- [functional] New tool “detect_address_poisoning_scam”

### 2026-10-21 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 58, +5)

- [security improvement] Authorization: unverified → partial
- [functional regression] Schema quality: 768 → 3009
- [functional regression] Tool coverage: 52% → 41%
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “ai_computer_use”
- [functional] New tool “ai_deep_research”
- [functional] New tool “ai_embeddings”
- [functional] New tool “ai_extract”
- [functional] New tool “ai_generate”
- [functional] New tool “ai_grounded_maps”
- [functional] New tool “ai_grounded_search”
- [functional] New tool “ai_image_gen”
- [functional] New tool “ai_music_gen”
- [functional] New tool “ai_omni”
- [functional] New tool “ai_robotics”
- [functional] New tool “ai_summarize”
- [functional] New tool “ai_tts”
- [functional] New tool “ai_video_gen”
- [functional] New tool “clean_data”
- [functional] New tool “crypto_address_poisoning_check”
- [functional] New tool “crypto_eip712_permit_decoder”
- [functional] New tool “crypto_utxo_consolidation_planner”
- [functional] New tool “eve_killmail_threat_intel”
- [functional] New tool “eve_sovereignty_fuel_radar”
- [functional] New tool “eve_ssu_market_maker”
- [functional] New tool “eve_sui_ptb_simulator”
- [functional] New tool “eve_turret_target_matrix”
- [functional] New tool “eve_zklogin_character_verifier”
- [functional] New tool “http402_challenge_verifier”
- [functional] New tool “mcp_rugpull_diff”
- [functional] New tool “mcp_sampling_guard”
- [functional] New tool “mempool_fee”
- [functional] New tool “mpp_agent_escrow_arbiter”
- [functional] New tool “mpp_session_infer”
- [functional] New tool “scrub_pii”
- [functional] New tool “swap_rate”
- [functional] New tool “tool_output_firewall”
- [functional] New tool “x402_embeddings”
- [functional] New tool “x402_solana_priority_fee_oracle”
- [functional] New tool “x402_token_meta”
- [functional] New tool “x402_whale_radar”
- [functional] New tool “ai_code_gen”
- [functional] New tool “ai_antigravity_agent”
- [functional] New tool “ai_audio_live”
- [functional] New tool “agent_context_compaction_verifier”
- [functional] New tool “agent_hallucination_auditor”
- [functional] New tool “agent_loop_circuit_breaker”
- [functional] New tool “agent_mcp_manifest_auditor”
- [functional] New tool “agent_prompt_compiler”
- [functional] New tool “agent_sql_guard”

### 2026-10-19 (score 53)

First indexed and scored.

## MCP tools (71)

### `verify_agent_command_safety` (~167 tokens)

Autonomous Agent Pre-Execution Command & Prompt Injection Gate

Evaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration. Use when screening a general shell command or user prompt before agent execution; for statically validating SQL database queries at the AST level, use validate_sql_query_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'payload' ('action_type' defaults to 'bash_command'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `action_type` (string): Execution context of the payload; defaults to 'bash_command' when omitted.
- `payload` (string, required): Raw command string, script snippet, or untrusted prompt to inspect for safety violations.

Output parameters:

- `risk_score` (number): Normalized threat probability from 0.0 (benign) to 1.0 (critical).
- `safe` (boolean): True when zero injection, exfiltration, or destructive patterns are found.
- `threats_detected` (array): List of specific threat categories triggered by the payload.
- `verdict` (string): Enforcement decision ('ALLOW', 'BLOCK', or 'QUARANTINE').

### `validate_sql_query_ast` (~190 tokens)

AST-Level Read-Only SQL Query & Injection Safety Validator

Performs static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypasses. Use when verifying that an agent-authored SQL statement is strictly read-only before running it on a database; for screening non-SQL bash commands or general agent prompts, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_statement' ('dialect' defaults to 'postgres'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

Input parameters:

- `dialect` (string): SQL dialect ruleset used for AST token inspection; defaults to 'postgres' when omitted.
- `sql_statement` (string, required): SQL statement string to statically parse and audit for read-only SELECT compliance (e.g. 'SELECT id, email FROM users WHERE active = 1').

Output parameters:

- `blocked_clauses` (array): List of destructive or injection SQL tokens detected.
- `safe_read_only` (boolean): True when the query is a pure SELECT statement with zero injection clauses.
- `tables_accessed` (array): Table identifiers referenced in FROM and JOIN clauses.
- `verdict` (string): Execution decision ('ALLOW_EXECUTION' or 'BLOCK_EXECUTION').

### `execute_python_sandbox` (~184 tokens)

AST-Audited Ephemeral Python Code Execution Sandbox

Audits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access. Use when executing LLM-generated Python snippets safely; for checking shell commands without executing code, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'python_script' ('timeout_profile' defaults to 'fast_1s'), supports '?demo=true' or MPP (1500 sats), and returns HTTP 400 if invalid.

Input parameters:

- `python_script` (string, required): Python 3 source script to audit and execute strictly inside an isolated AST-governed, non-privileged WebAssembly sandbox with no host filesystem access.
- `timeout_profile` (string): Execution resource ceiling; defaults to 'standard_5s' when omitted.

Output parameters:

- `ast_security_audit` (object): Static syscall audit summary including flagged_calls and safety_verdict.
- `exit_code` (integer): Process exit status (0 on clean execution, 1 on security block).
- `simulated_stdout` (string): Captured standard output from the isolated execution.
- `syntax_valid` (boolean): True if the Python source parses without syntax errors.

### `audit_mcp_server_manifest` (~186 tokens)

External MCP Server Manifest & Tool-Poisoning Security Auditor

Scans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptions. Use when vetting a newly discovered third-party MCP server before mounting it into an agent session; for comparing a previously pinned MCP baseline against a live mid-session tools/list response, use detect_mcp_schema_rugpull instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'manifest_json' ('audit_profile' defaults to 'strict'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

Input parameters:

- `audit_profile` (string): Sensitivity level for flagging system-tool name shadowing; defaults to 'strict' when omitted.
- `manifest_json` (string, required): JSON string or object containing the external MCP server's tools array to audit.

Output parameters:

- `manifest_safe` (boolean): True if zero shadowed tools or description injections are found.
- `security_grade` (string): Overall manifest safety grade ('A+', 'C', or 'F').
- `shadowed_tools` (array): Tool names attempting to shadow host privileges (e.g. 'bash', 'read_file').
- `suspicious_tools` (array): Tools containing covert prompt-injection or exfiltration instructions.

### `detect_mcp_schema_rugpull` (~209 tokens)

Mid-Session MCP tools/list Rug-Pull & Schema Mutation Detector

Computes structural diffs between a pinned baseline MCP tools/list snapshot and a live server response to catch mid-session description or schema tampering. Use when verifying that a connected MCP server has not mutated its tool definitions mid-session; for performing a first-time static security audit on a single MCP manifest, use audit_mcp_server_manifest instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'baseline_tools_json' ('current_tools_json' defaults to 'standard'), supports '?demo=true' or L402 (85 sats), and returns HTTP 400 if invalid.

Input parameters:

- `baseline_tools_json` (string, required): JSON-serialized baseline tools/list array captured when the MCP server was first trusted.
- `current_tools_json` (string): JSON-serialized live tools/list array to compare against the baseline; defaults to '[]' when omitted.
- `diff_mode` (string): Comparison strictness across descriptions and inputSchema; defaults to 'full_structural' when omitted.

Output parameters:

- `mutated_tools` (array): Detailed list of modified tools and their exact mutation type.
- `rugpull_detected` (boolean): True if any tool was surreptitiously added or had its description/schema altered.
- `timestamp_utc` (string): ISO-8601 UTC timestamp of the diff audit.
- `verdict` (string): Connection verdict ('SCHEMA_INTEGRITY_VERIFIED' or 'REVOKE_MCP_SERVER_IMMEDIATELY').

### `validate_mcp_sampling_request` (~179 tokens)

Inbound MCP sampling/createMessage Reverse-Injection Firewall

Audits inbound MCP sampling/createMessage callbacks from connected servers to block cross-server context snooping (includeContext='allServers') and token quota hijacking. Use when filtering a connected MCP server's request to sample the host LLM; for scrubbing text returned from a standard synchronous tools/call response, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sampling_request_json' ('max_tokens_ceiling' defaults to '512'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `max_tokens_ceiling` (string): Maximum completion token quota allowed for server callbacks; defaults to '2048' when omitted.
- `sampling_request_json` (string, required): JSON string or object representing the inbound MCP sampling/createMessage payload.

Output parameters:

- `recommended_action` (string): Host enforcement action ('APPROVE_SAMPLING_REQUEST' or 'REJECT_SAMPLING_REQUEST').
- `sampling_safe` (boolean): True if the sampling request respects context isolation and token caps.
- `timestamp_utc` (string): ISO-8601 UTC timestamp of the inspection.
- `violations_detected` (array): Specific policy violations found in the sampling request.

### `sanitize_tool_output_stream` (~186 tokens)

Indirect Prompt-Injection, Invisible Unicode & Beacon Output Scrubber

Sanitizes untrusted external tool or web-scrape outputs by stripping invisible Unicode Tag characters (U+E0000), neutralizing Markdown tracking image beacons, and defusing indirect prompt overrides. Use when cleaning raw third-party tool outputs or scraped web text before inserting it into the LLM context window; for redacting personal identifiable information (emails, SSNs, keys) from outbound text, use redact_sensitive_pii instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_tool_output' (with enum defaults), uses '?demo=true' or L402 (75 sats); HTTP 400 if invalid.

Input parameters:

- `raw_tool_output` (string, required): Untrusted text returned by an external tool, webhook, or web scraper.
- `wrap_tag` (string): XML isolation wrapper applied around the sanitized text; defaults to 'tool_data' when omitted.

Output parameters:

- `injection_risk_score` (number): Threat score from 0.0 to 0.99 prior to sanitization.
- `safe_for_context_ingestion` (boolean): True once the sanitized payload is safe to feed to the LLM.
- `sanitized_output` (string): Cleaned text with invisible Unicode, tracking beacons, and overrides neutralized.
- `threats_neutralized` (array): List of smuggling or injection vectors stripped from the input.

### `redact_sensitive_pii` (~169 tokens)

Zero-PII & Secret Credential Redaction Engine

Redacts emails, phone numbers, SSNs, credit cards, API keys, and crypto private keys from text before logging or external transmission. Use when stripping personal data or secret credentials from prompts, logs, or outbound messages; for neutralizing indirect prompt injections and invisible Unicode in inbound tool responses, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('redaction_style' defaults to 'typed_token'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

Input parameters:

- `redaction_style` (string): Placeholder format used for redacted spans; defaults to 'typed_token' when omitted.
- `text` (string, required): Input text containing potential PII or secret keys to redact.

Output parameters:

- `categories_redacted` (array): Types of sensitive data detected (e.g. 'EMAIL', 'SSN', 'PRIVATE_KEY').
- `redactions_count` (integer): Total number of sensitive entities redacted.
- `scrubbed_text` (string): Sanitized text with all sensitive entities replaced by redaction tokens.
- `zero_pii_certified` (boolean): True when post-scan verification confirms zero residual PII patterns.

### `detect_agent_action_loop` (~185 tokens)

Autonomous Agent Action-Trace Loop & Token-Burn Circuit Breaker

Analyzes an agent's recent tool-call trace to detect identical retry spins, A/B state oscillation, and runaway token burn. Use when monitoring multi-step agent execution loops to decide whether to continue or halt and escalate; for inspecting a single command payload for security threats before execution, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'action_trace_json' ('sensitivity' defaults to 'strict_2_repeats'), supports '?demo=true' or L402 (70 sats), and returns HTTP 400 if invalid.

Input parameters:

- `action_trace_json` (string, required): JSON-serialized array of recent agent actions (e.g. '[{"tool":"search","status":"err"}]').
- `sensitivity` (string): Cycle detection threshold; defaults to 'standard_3_repeats' when omitted.

Output parameters:

- `circuit_breaker_action` (string): Recommended control action ('CONTINUE_EXECUTION' or 'HALT_AND_ESCALATE_OR_SWITCH_TOOL').
- `estimated_tokens_saved` (integer): Projected token burn prevented by tripping the circuit breaker.
- `loop_detected` (boolean): True if a repetitive retry spin or A/B oscillation cycle is active.
- `loop_pattern` (string): Detected cycle topology ('NONE', 'IDENTICAL_RETRY_SPIN', or 'ABAB_STATE_OSCILLATION').

### `verify_a2a_agent_card` (~200 tokens)

A2A /.well-known/agent.json Identity & Capability Card Verifier

Verifies a remote agent's A2A /.well-known/agent.json discovery card, checking JWS/DID signature binding, endpoint HTTPS enforcement, and capability spoofing. Use when authenticating a peer autonomous agent before delegating subtasks or exchanging payments over A2A; for auditing an MCP tool server's tools/list manifest rather than a peer agent's A2A card, use audit_mcp_server_manifest instead. Read-only edge call (32 KB, 60 RPM): accepts 'agent_card_json' ('trust_policy' defaults to 'require_https_and_did'), supports '?demo=true' or L402 (90 sats), and returns HTTP 400 if invalid.

Input parameters:

- `agent_card_json` (string, required): JSON string or object of the peer agent's /.well-known/agent.json descriptor.
- `trust_policy` (string): Verification policy for DID/DNS binding; defaults to 'require_https_and_did' when omitted.

Output parameters:

- `agent_id` (string): Canonical identifier of the verified peer agent.
- `card_valid` (boolean): True when the A2A agent card schema, transport, and identity claims pass verification.
- `delegation_verdict` (string): Handshake decision ('SAFE_TO_DELEGATE_A2A' or 'REJECT_UNVERIFIED_AGENT').
- `spoofing_flags` (array): List of impersonation or downgrade anomalies detected.

### `audit_outbound_egress_url` (~198 tokens)

Outbound Agent URL SSRF, Metadata & Secret Exfiltration Firewall

Static validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltration before agent dispatch. Use when validating a user-supplied or tool-supplied URI destination before network dispatch; for auditing local shell commands or general prompts, use verify_agent_command_safety instead. Read-only edge call (32 KB, 60 RPM): accepts 'destination_uri' ('egress_policy' defaults to 'block_private_and_metadata'), supports '?demo=true' or L402 (65 sats), and returns HTTP 400 if invalid.

Input parameters:

- `destination_uri` (string, required): Outbound HTTP/HTTPS destination URI to inspect before fetching (e.g. 'https://api.example.com/v1/webhook').
- `egress_policy` (string): Network egress policy; defaults to 'block_private_and_metadata' when omitted.

Output parameters:

- `egress_allowed` (boolean): True if the URL targets a safe public endpoint with no exfiltration tokens.
- `exfiltration_query_params` (array): Query parameters suspected of carrying leaked secrets or base64 payloads.
- `ssrf_risk_detected` (boolean): True if loopback, RFC1918 private IP, or cloud metadata IP is targeted.
- `verdict` (string): Firewall decision ('ALLOW_EGRESS_REQUEST' or 'BLOCK_SSRF_OR_EXFIL').

### `audit_response_factuality` (~197 tokens)

Draft Agent Response Groundedness & Hallucination Auditor

Cross-references factual claims, numbers, and citations in a draft agent response against retrieved source passages to flag unsupported hallucinations before delivery. Use when verifying that a generated answer is 100% grounded in source evidence before returning it to the user; for scrubbing inbound tool outputs for prompt-injection and invisible Unicode, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim' ('context' defaults to 'standard'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

Input parameters:

- `claim` (string, required): Draft agent response or factual statement to verify for hallucinations.
- `context` (string, required): Authoritative source text or retrieved RAG passages that the claim must be grounded in.
- `strictness` (string): Entailment threshold required for numbers and dates; defaults to 'exact_entailment' when omitted.

Output parameters:

- `groundedness_score` (number): Factual support ratio from 0.0 (fabricated) to 1.0 (fully entailed).
- `unverified_claims` (array): Hallucinated or unsupported assertions flagged for removal.
- `verdict` (string): Audit outcome ('PASS', 'SUSPICIOUS', or 'FAIL').
- `verified_claims` (array): Assertions directly entailed by the provided source context.

### `audit_smart_contract_code` (~188 tokens)

EVM & Move Smart Contract Honeypot, Tax & Reentrancy Auditor

Statically audits Solidity, Vyper, or Move smart contract source code for honeypot transfer taxes, hidden mint backdoors, proxy upgrade traps, and reentrancy. Use when auditing smart contract source code or bytecode before deploying or interacting with a protocol; for scanning Solana Anchor/Rust programs specifically for Cross-Program Invocation (CPI) signer/account vulnerabilities, use scan_solana_cpi_reentrancy instead. Read-only edge call (32 KB, 60 RPM): accepts 'code_or_address' ('chain' defaults to 'evm_solidity'), uses '?demo=true' or L402 (250 sats); HTTP 400 if invalid.

Input parameters:

- `chain` (string): Target blockchain VM architecture; defaults to 'evm_solidity' when omitted.
- `code_or_address` (string, required): Smart contract source code snippet, ABI, or contract address to audit.

Output parameters:

- `is_honeypot` (boolean): True if transfer restrictions or excessive sell taxes (>10%) are present.
- `risk_level` (string): Severity classification ('LOW', 'MEDIUM', 'HIGH', or 'CRITICAL').
- `security_score` (integer): Composite contract safety score from 0 (critical exploit) to 100 (verified safe).
- `vulnerabilities` (array): Specific vulnerability findings and line-level remediation advice.

### `scan_solana_cpi_reentrancy` (~190 tokens)

Solana Anchor & Rust Cross-Program Invocation (CPI) Vulnerability Scanner

Scans Solana Anchor and native Rust program instructions for unverified Cross-Program Invocation (CPI) program IDs, missing signer checks, and PDA bump seed canonicalization bugs. Use when auditing Solana Rust/Anchor source code or instruction account structs for CPI privilege escalation; for checking live SPL token mint/freeze authorities and rug-pull risk by mint address, use evaluate_solana_token_risk instead. Read-only edge call (32 KB, 60 RPM): accepts 'rust_source_or_idl' ('framework' defaults to 'anchor'), uses '?demo=true' or L402 (160 sats); HTTP 400 if invalid.

Input parameters:

- `framework` (string): Solana program framework used; defaults to 'anchor' when omitted.
- `rust_source_or_idl` (string, required): Solana Rust/Anchor source code or IDL JSON string to scan for CPI vulnerabilities.

Output parameters:

- `arbitrary_cpi_detected` (boolean): True if invoke/invoke_signed is called without validating the target program account.
- `audit_verdict` (string): Overall Solana program verdict ('SAFE_ANCHOR_PROGRAM' or 'CRITICAL_CPI_VULNERABILITY').
- `missing_signer_checks` (array): Accounts mutated without enforcing Signer<'info> or has_one constraints.
- `pda_bump_safe` (boolean): True when canonical bump seeds are enforced on all PDA derivations.

### `evaluate_solana_token_risk` (~191 tokens)

Solana SPL Token Mint/Freeze Authority & Rug-Pull Risk Evaluator

Evaluates a Solana SPL token's rug-pull probability by checking active mint authority, freeze authority, mutable metadata, and top-holder concentration. Use when making a pre-trade security decision on whether a Solana SPL token is safe to buy; for retrieving SPL token symbol, decimals, and DEX liquidity pool metadata via x402, use inspect_solana_token_liquidity instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'token_address' ('risk_profile' defaults to 'strict_decentralized'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `risk_profile` (string): Tolerance policy for centralized freeze authorities; defaults to 'strict_decentralized' when omitted.
- `token_address` (string, required): Base58-encoded Solana SPL token mint address (32–44 characters).

Output parameters:

- `freeze_authority_present` (boolean): True if an active authority can freeze holder token accounts.
- `risk_score` (number): Rug-pull risk score from 0.0 (renounced/safe) to 1.0 (critical danger).
- `should_transact` (boolean): True when the token passes authority and concentration safety checks.
- `valid_base58` (boolean): True when the provided address is a valid Base58 Solana public key.

### `inspect_solana_token_liquidity` (~204 tokens)

Solana SPL Token Metadata, Decimals & Authority Registry Lookup

Retrieves canonical Solana SPL token metadata including name, ticker symbol, decimal precision, and current mint/freeze authority addresses. Use when resolving SPL token decimals, ticker symbols, and registry metadata for portfolio or swap formatting; for computing a composite security risk score and binary should_transact verdict, use evaluate_solana_token_risk instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'mint' ('network' defaults to 'mainnet-beta'), supports '?demo=true' or x402 (200 sats), and returns HTTP 400 if invalid.

Input parameters:

- `mint` (string, required): Base58-encoded Solana SPL token mint address (e.g. 'EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v').
- `network` (string): Solana cluster to query; defaults to 'mainnet-beta' when omitted.

Output parameters:

- `authorities_renounced` (boolean): True when both mint_authority and freeze_authority are null.
- `decimals` (integer): Token decimal precision used for raw lamport/atomic unit conversion.
- `mint` (string): Queried Base58 SPL token mint address.
- `symbol` (string): Canonical token ticker symbol (e.g. 'USDC', 'SOL', 'JUP').

### `track_solana_whale_flows` (~172 tokens)

Solana Whale Wallet Net-Flow & Insider Cluster Tracker

Tracks 24-hour net accumulation or distribution flows across top Solana whale wallets and flags coordinated insider wallet clusters for a given SPL token. Use when analyzing on-chain smart-money order flow and holder clustering on Solana; for checking static SPL contract mint/freeze authority permissions, use evaluate_solana_token_risk instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'token' ('window' defaults to '1h'), supports '?demo=true' or x402 (500 sats), and returns HTTP 400 if invalid.

Input parameters:

- `token` (string, required): Base58 Solana SPL token mint address or ticker symbol to track whale flows for.
- `window` (string): Aggregation lookback window for net whale flow; defaults to '24h' when omitted.

Output parameters:

- `insider_cluster_detected` (boolean): True if synchronized funding patterns indicate an insider wallet cluster.
- `net_flow_24h_usd` (string): Signed 24-hour net whale flow denominated in USD.
- `signal` (string): Order-flow classification ('ACCUMULATION' or 'DISTRIBUTION').
- `token` (string): Tracked Solana token identifier.

### `estimate_solana_priority_fees` (~177 tokens)

Solana Compute-Unit Priority Fee & Jito MEV Tip Estimator

Calculates optimal Solana compute-unit (CU) microlamport priority fees and Jito bundle tip lamports to achieve target block-inclusion probability. Use when setting SetComputeUnitPrice and Jito tips before broadcasting a Solana transaction; for querying Bitcoin L1 sat/vB mempool fee rates, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'priority_level' ('tx_type' defaults to 'simple_transfer'), supports '?demo=true' or x402 (50 sats), and returns HTTP 400 if invalid.

Input parameters:

- `priority_level` (string, required): Target inclusion urgency tier on Solana mainnet-beta.
- `tx_type` (string): Transaction category used to estimate compute unit limit; defaults to 'dex_swap' when omitted.

Output parameters:

- `estimated_landing_probability` (number): Projected next-block inclusion probability (0.0 to 1.0).
- `recommended_compute_unit_limit` (integer): Suggested ComputeBudget compute unit ceiling.
- `recommended_jito_tip_lamports` (integer): Recommended Jito block-engine tip in lamports for MEV-protected landing.
- `recommended_micro_lamports_per_cu` (integer): Recommended priority fee in microlamports per compute unit.

### `decode_eip712_permit_signature` (~205 tokens)

EIP-712 Typed Data & Uniswap Permit2 Phishing Signature Decoder

Decodes EIP-712 and Uniswap Permit2 off-chain typed-data payloads to verify spender identity, detect unlimited (uint256.max) token approvals, and flag expired deadlines. Use when inspecting an off-chain eth_signTypedData_v4 or Permit2 payload before signing; for decoding raw on-chain hex transaction calldata (0x...) for eth_sendTransaction, use simulate_evm_transaction_calldata instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'typed_data_json' ('chain_id' defaults to '1'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `chain_id` (string): EVM chain ID used to verify canonical router spender addresses; defaults to '8453' (Base) when omitted.
- `typed_data_json` (string, required): JSON string or object containing the EIP-712 / Permit2 message (spender, amount, deadline).

Output parameters:

- `signing_verdict` (string): Safety recommendation ('SAFE_BOUNDED_PERMIT' or 'CRITICAL_UNLIMITED_APPROVAL_UNVERIFIED_SPENDER').
- `spender_address` (string): Normalized lowercase EVM address of the permit spender.
- `spender_identity` (string): Identified protocol router label or 'Unknown Third-Party Spender'.
- `unlimited_approval_detected` (boolean): True if the approval value equals uint256.max / uint160.max.

### `simulate_evm_transaction_calldata` (~216 tokens)

Pre-Sign EVM Hex Calldata Selector Decoder & Drain Simulator

Decodes raw EVM hexadecimal transaction calldata (0x...) by 4-byte function selector to expose hidden ERC-20 approve/transferFrom calls, setApprovalForAll drains, and multicall bundles. Use when auditing raw hex transaction data (to, value, data) before broadcasting an on-chain EVM transaction; for inspecting off-chain EIP-712 JSON typed-data signatures, use decode_eip712_permit_signature instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'calldata_hex' ('network' defaults to 'base_mainnet'), supports '?demo=true' or L402 (90 sats), and returns HTTP 400 if invalid.

Input parameters:

- `calldata_hex` (string, required): Hexadecimal EVM transaction data string starting with '0x' (e.g. '0x095ea7b3000000000000000000000000...').
- `network` (string): Target EVM network for simulation context; defaults to 'base_mainnet' when omitted.

Output parameters:

- `approval_or_drain_risk` (boolean): True if the call grants token/NFT allowances or transfers assets to an untrusted target.
- `decoded_method` (string): Human-readable ABI function signature matched to the selector.
- `selector_hex` (string): Extracted 4-byte function selector (e.g. '0x095ea7b3').
- `simulation_verdict` (string): Pre-sign safety recommendation ('SAFE_CALLDATA' or 'HIGH_RISK_APPROVAL_DETECTED').

### `evaluate_dex_mev_risk` (~193 tokens)

Pre-Swap DEX MEV Sandwich & Frontrunning Risk Evaluator

Evaluates decentralized exchange (DEX) swap parameters against pool depth and mempool visibility to quantify MEV sandwich risk and compute optimal slippage tolerance in basis points. Use when configuring slippage tolerance and private-RPC routing before executing an on-chain DEX token swap; for comparing cross-chain bridge settlement routes across different L1 blockchains, use compare_crosschain_bridge_routes instead. Read-only edge call (32 KB, 60 RPM): accepts 'pair' ('execution_venue' defaults to 'uniswap_v3_public'), uses '?demo=true' or L402 (150 sats); HTTP 400 if invalid.

Input parameters:

- `execution_venue` (string): Target DEX protocol or RPC relay; defaults to 'uniswap_v3_public' when omitted.
- `pair` (string, required): Trading pair symbol or pool identifier (e.g. 'ETH/USDC' or 'SOL/USDC').

Output parameters:

- `frontrunning_detected` (boolean): True if public mempool broadcast exposes the swap to predatory bots.
- `optimal_slippage_bps` (integer): Recommended maximum slippage tolerance in basis points (1 bps = 0.01%).
- `recommended_rpc` (string): Suggested MEV-protected broadcast endpoint.
- `sandwich_risk` (string): Assessed MEV extraction risk tier ('LOW', 'MEDIUM', or 'HIGH').

### `detect_address_poisoning_scam` (~171 tokens)

Counterparty Address Poisoning & Vanity Prefix/Suffix Spoof Detector

Compares a target recipient wallet address against recent transaction history to detect vanity prefix/suffix lookalike spoofing and zero-value dusting attacks. Use when verifying a recipient EVM or Solana wallet address before sending funds; for decoding hex smart contract calldata payloads, use simulate_evm_transaction_calldata instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_address' ('address_standard' defaults to 'auto_detect'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `address_standard` (string): Address encoding format; defaults to 'auto_detect' when omitted.
- `target_address` (string, required): Candidate recipient EVM (0x...) or Solana Base58 wallet address to verify.

Output parameters:

- `poisoning_detected` (boolean): True if a prefix/suffix collision with a different middle body is found.
- `prefix_suffix_collision_score` (number): Similarity score (0.0 to 1.0) against known counterparty addresses.
- `target_address` (string): Audited recipient address.
- `verdict` (string): Transfer safety decision ('SAFE_VERIFIED' or 'DANGER_POISONING_ATTACK').

### `verify_http402_payment_challenge` (~202 tokens)

Pre-Payment HTTP 402 (L402 / x402 / MPP) Invoice & Macaroon Fraud Verifier

Decodes inbound HTTP 402 Payment Required challenges (L402 BOLT11 + Macaroon, x402 Solana USDC, MPP Base intents) to verify cryptographic payment-hash binding and block overcharge fraud. Use when auditing a 402 challenge header before an autonomous agent pays a Lightning invoice or USDC transfer; for checking on-chain Bitcoin L1 mempool feerates, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'www_authenticate' ('protocol_hint' defaults to 'L402'), supports '?demo=true' or L402 (60 sats), and returns HTTP 400 if invalid.

Input parameters:

- `protocol_hint` (string): Expected HTTP 402 payment protocol; defaults to 'L402' when omitted.
- `www_authenticate` (string, required): Raw WWW-Authenticate or Payment-Required HTTP header string from a 402 response.

Output parameters:

- `macaroon_payment_hash_matches_bolt11` (boolean): True when the macaroon caveat hash matches the BOLT11 invoice payment hash.
- `overcharge_detected` (boolean): True if the invoice amount exceeds the declared endpoint price ceiling.
- `payment_safety_verdict` (string): Authorization recommendation ('SAFE_TO_PAY' or 'REJECT_HASH_MISMATCH').
- `protocol_detected` (string): Identified 402 settlement protocol ('L402', 'x402', or 'MPP').

### `estimate_bitcoin_mempool_fees` (~162 tokens)

Bitcoin Mainnet Mempool Feerate Estimator (sat/vB)

Fetches real-time Bitcoin mainnet mempool feerate recommendations in satoshis per virtual byte (sat/vB) across fastest, half-hour, hour, and economy confirmation tiers. Use when checking current Bitcoin L1 network congestion before broadcasting an on-chain BTC transaction; for calculating exact SegWit/Taproot UTXO batch consolidation vByte weights and dust thresholds, use plan_bitcoin_utxo_consolidation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'confirmation_target', supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

Input parameters:

- `confirmation_target` (string): Target confirmation speed tier; defaults to 'half_hour' when omitted.

Output parameters:

- `economyFee` (integer): Low-priority feerate in sat/vB for non-urgent batch sweeps.
- `fastestFee` (integer): Recommended feerate in sat/vB for next-block (~10 min) inclusion.
- `halfHourFee` (integer): Recommended feerate in sat/vB for ~30-minute confirmation.
- `hourFee` (integer): Recommended feerate in sat/vB for ~60-minute confirmation.

### `plan_bitcoin_utxo_consolidation` (~234 tokens)

Bitcoin SegWit/Taproot UTXO Dust Consolidation & Fee-Window Planner

Analyzes a set of Bitcoin UTXO balances in satoshis to compute exact vByte transaction weight, identify uneconomical dust inputs, and recommend whether to consolidate now or hold. Use when optimizing on-chain Bitcoin treasury UTXO sets to minimize long-term miner fee drag; for fetching current live Bitcoin mempool sat/vB feerates alone, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'utxos_sats_json' ('script_type' defaults to 'p2wpkh_segwit'), supports '?demo=true' or L402 (80 sats), and returns HTTP 400 if invalid.

Input parameters:

- `script_type` (string): Bitcoin input script type determining vByte weight per input; defaults to 'p2wpkh_segwit' when omitted.
- `utxos_sats_json` (string, required): JSON array or comma-separated list of UTXO values in satoshis (e.g. '[1200, 45000, 85000]').

Output parameters:

- `estimated_consolidation_vbytes` (integer): Total virtual byte (vB) size of the consolidation transaction.
- `high_fee_dust_utxos` (integer): Count of UTXOs whose input weight costs more than 3% of their value.
- `recommended_action` (string): Execution timing advice ('CONSOLIDATE_NOW' or 'HOLD_UNTIL_SUB_15_SAT_VB').
- `utxo_count` (integer): Number of UTXO inputs analyzed.

### `calculate_spot_swap_rate` (~165 tokens)

Cross-Asset Spot Exchange Rate & Satoshi Conversion Calculator

Calculates instantaneous spot exchange rates and equivalent USD, BTC, and satoshi values across BTC, ETH, SOL, SUI, and USDC. Use when converting a token amount into USD or satoshis for invoice pricing or accounting; for quoting executable non-KYC cross-chain bridge routes with bridge fees and settlement times, use compare_crosschain_bridge_routes instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'currency' ('amount' defaults to 'standard'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `amount` (number): Quantity of the source asset to convert; defaults to 100 when omitted.
- `currency` (string, required): Source asset ticker symbol to convert from.

Output parameters:

- `equivalent_sats` (integer): Equivalent value denominated in Bitcoin satoshis.
- `source_amount` (number): Input asset quantity.
- `source_currency` (string): Input asset symbol converted.
- `total_usd_value` (number): Equivalent spot value in US Dollars (USD).

### `compare_crosschain_bridge_routes` (~204 tokens)

Non-KYC Cross-Chain Bridge Route & Settlement Fee Comparator

Compares non-custodial, non-KYC cross-chain swap routes (THORChain native L1 swaps, Maya Protocol, Blockstream Liquid) by basis-point fee, net output sats, and settlement time. Use when routing cross-chain treasury settlements (e.g. Solana USDC or Base ETH into native Bitcoin); for calculating mid-market spot exchange rates without bridge routing fees, use calculate_spot_swap_rate instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'from_asset' ('to_asset' defaults to 'BTC_NATIVE'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `amount` (number): Input asset amount to quote; defaults to 100.0 when omitted.
- `from_asset` (string, required): Origin chain asset identifier to bridge from.
- `to_asset` (string): Destination chain asset identifier; defaults to 'BTC_NATIVE' when omitted.

Output parameters:

- `best_route` (string): Optimal non-KYC bridge protocol selected (e.g. 'THORCHAIN_NATIVE_SWAP').
- `estimated_output_sats` (integer): Net settled output denominated in Bitcoin satoshis.
- `fee_bps` (integer): Total protocol and slip fee in basis points.
- `kyc_required` (boolean): Always false; only non-custodial permissionless routes are returned.

### `generate_gemini_completion` (~191 tokens)

Account-Less Google Gemini 4 Argon & 3.1 Pro Universal Text Generator

Generates text completions and structured reasoning across all 45 Google Gemini foundation models (Gemini 4 Argon, 3.1 Pro, 3.8 Flash) with zero Google account or API key required. Use when running single-turn reasoning, coding, or analytical prompts on a specific Gemini model; for delegating multi-step autonomous tasks that require remote tool execution, use execute_antigravity_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('model' defaults to 'gemini-4-argon'), supports '?demo=true' or L402 (250 sats), and returns HTTP 400 if invalid.

Input parameters:

- `model` (string): Target Gemini foundation model identifier; defaults to 'gemini-4-argon' when omitted.
- `prompt` (string, required): Primary user instruction or reasoning prompt to send to the selected Gemini model.

Output parameters:

- `grounding_metadata` (object): Optional citation metadata if search grounding was enabled.
- `model` (string): Gemini model identifier that executed the completion.
- `output` (string): Generated model response text.
- `success` (boolean): True when inference completed without upstream errors.

### `execute_antigravity_agent` (~171 tokens)

Google Antigravity Multi-Step Autonomous Coding & Workflow Agent

Dispatches a complex engineering or operational task to Google's Antigravity autonomous agent for multi-step planning, tool orchestration, and verified execution. Use when solving multi-stage software engineering or workflow tasks that require autonomous planning; for compiling exhaustive multi-source literature and market research dossiers, use conduct_deep_research_investigation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('execution_mode' defaults to 'autonomous_verified'), supports '?demo=true' or L402 (500 sats), and returns HTTP 400 if invalid.

Input parameters:

- `execution_mode` (string): Autonomy policy for subtask execution; defaults to 'autonomous_verified' when omitted.
- `input` (string, required): High-level task objective and constraints for the Antigravity autonomous agent.

Output parameters:

- `agent` (string): Autonomous agent identifier ('antigravity-preview-latest').
- `environment` (string): Execution environment ('remote').
- `output` (string): Synthesized final deliverable and action trace summary.
- `success` (boolean): True when the agent completed all planned steps.

### `conduct_deep_research_investigation` (~177 tokens)

Gemini Deep Research Pro Multi-Hop Investigative Analyst

Runs an iterative, multi-hop investigative research session via Gemini Deep Research Pro, cross-examining primary sources to produce a cited technical report. Use when investigating complex scientific, architectural, or market questions requiring deep multi-hop synthesis; for running a fast single-turn Google Search grounded fact lookup, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('depth_tier' defaults to 'quick_synthesis'), supports '?demo=true' or L402 (1000 sats), and returns HTTP 400 if invalid.

Input parameters:

- `depth_tier` (string): Research breadth and citation density; defaults to 'exhaustive_report' when omitted.
- `input` (string, required): Investigative research question, scope, and specific aspects to analyze.

Output parameters:

- `agent` (string): Deep Research engine identifier ('deep-research-preview-04-2026').
- `output` (string): Comprehensive multi-section investigative report with inline citations.
- `sources_count` (integer): Number of independent sources cross-referenced.
- `success` (boolean): True when the research synthesis completed.

### `operate_computer_use_agent` (~173 tokens)

Gemini Computer Use GUI & Browser Action Planner

Plans and executes OS-level desktop, browser DOM, and GUI coordinate actions (click, type, scroll, wait) using the Gemini Computer Use agent. Use when automating interactive web UIs or desktop workflows that lack a direct REST API; for running code-first API and terminal automation tasks, use execute_antigravity_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('viewport_preset' defaults to 'desktop_1080p'), supports '?demo=true' or L402 (800 sats), and returns HTTP 400 if invalid.

Input parameters:

- `input` (string, required): UI automation goal and target webpage or application context.
- `viewport_preset` (string): Target screen resolution for coordinate grounding; defaults to 'desktop_1080p' when omitted.

Output parameters:

- `agent` (string): Computer Use model identifier ('computer-use-preview-2026').
- `output` (string): Executed UI action sequence and extracted screen state.
- `steps_executed` (integer): Number of GUI interaction steps performed.
- `success` (boolean): True when the UI workflow reached the target state.

### `search_gemini_grounded_web` (~181 tokens)

Google Search Grounded Real-Time Fact & Citation Engine

Answers factual queries with live Google Search grounding, returning verified up-to-date answers accompanied by source URLs and grounding metadata. Use when verifying live web facts, documentation updates, or current events in a single low-latency call; for querying geographic places, coordinates, directions, and local business data via Google Maps grounding, use search_gemini_grounded_maps instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('recency_bias' defaults to 'past_24h'), supports '?demo=true' or L402 (200 sats), and returns HTTP 400 if invalid.

Input parameters:

- `prompt` (string, required): Factual question or search query to ground against live Google Search results.
- `recency_bias` (string): Temporal preference for search snippets; defaults to 'any_time' when omitted.

Output parameters:

- `citations` (object): Structured Google Search grounding chunks and source URLs.
- `grounding` (string): Grounding source ('google_search').
- `model` (string): Gemini model used for grounded synthesis.
- `output` (string): Grounded factual answer text.

### `search_gemini_grounded_maps` (~169 tokens)

Google Maps Grounded Geospatial & Place Intelligence Engine

Executes geospatial and point-of-interest queries grounded in live Google Maps data, returning verified addresses, coordinates, operating hours, and spatial context. Use when resolving physical locations, venues, transit distances, or regional infrastructure data; for searching general web articles, documentation, and news, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('distance_units' defaults to 'metric_km'), supports '?demo=true' or L402 (250 sats), and returns HTTP 400 if invalid.

Input parameters:

- `distance_units` (string): Preferred unit system for distances; defaults to 'metric_km' when omitted.
- `prompt` (string, required): Geospatial query, place name, or regional routing question.

Output parameters:

- `grounding` (string): Grounding source ('google_maps').
- `model` (string): Gemini model used for geospatial synthesis.
- `output` (string): Geospatially grounded response with place details.
- `places` (object): Structured Google Maps place identifiers and coordinates.

### `compile_mpp_research_dossier` (~190 tokens)

Base MPP Session-Metered Multi-Source Research Dossier Compiler

Compiles a structured JSON research dossier ('key_findings', 'synthesis_quality_score', 'sources_cited') settled via Base EVM Machine Payments Protocol (MPP). Use when generating a strict-JSON cited intelligence brief paid via Base USDC MPP session headers; for running long-form narrative research reports via L402 Lightning, use conduct_deep_research_investigation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('output_density' defaults to 'concise_5_points'), supports '?demo=true' or MPP (1000 sats), and returns HTTP 400 if invalid.

Input parameters:

- `output_density` (string): Granularity of the key_findings array; defaults to 'executive_10_points' when omitted.
- `query` (string): Research topic or technical question to investigate and structure into JSON.

Output parameters:

- `key_findings` (array): High-density factual bullet strings synthesized from live sources.
- `query` (string): Investigated research query.
- `sources_cited` (array): Verified grounding source references.
- `synthesis_quality_score` (integer): Self-audit completeness score from 90 to 100.

### `generate_gemini_embeddings` (~180 tokens)

Gemini Embedding 2 High-Dimensional (3,072-D) Vector Generator

Generates normalized 3,072-dimensional or 768-dimensional semantic vector embeddings via Google Gemini Embedding 2 for RAG indexing and cosine-similarity search. Use when embedding text passages or queries via L402 Lightning with configurable Matryoshka dimensions; for running live Google Search grounded factual queries, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('model' defaults to 'gemini-embedding-2'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

Input parameters:

- `model` (string): Gemini embedding model version; defaults to 'gemini-embedding-2' when omitted.
- `text` (string, required): Input text passage, code snippet, or search query to embed into a float vector.

Output parameters:

- `dimensions` (integer): Vector dimensionality returned (e.g. 3072 or 768).
- `embedding` (array): Normalized floating-point embedding vector.
- `model` (string): Embedding model executed.
- `success` (boolean): True when vector generation succeeded.

### `analyze_omni_multimodal_input` (~169 tokens)

Gemini Omni Unified Text, Audio & Video Multimodal Analyzer

Analyzes combined multimodal prompts spanning text, image descriptors, audio transcripts, and video temporal events using Gemini Omni Flash. Use when correlating information across multiple media modalities in a single reasoning pass; for running pure text-only reasoning or coding prompts, use generate_gemini_completion instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('modality_focus' defaults to 'cross_modal_synthesis'), supports '?demo=true' or L402 (300 sats), and returns HTTP 400 if invalid.

Input parameters:

- `input` (string, required): Multimodal prompt or media scene description to analyze.
- `modality_focus` (string): Primary analytical lens applied to the multimodal input; defaults to 'cross_modal_synthesis' when omitted.

Output parameters:

- `modalities_processed` (array): Modalities integrated during inference.
- `model` (string): Executed multimodal model ('gemini-omni-flash').
- `output` (string): Unified multimodal analysis and extracted timeline.
- `success` (boolean): True when multimodal processing succeeded.

### `plan_robotics_spatial_trajectory` (~175 tokens)

Gemini Robotics ER 2 Embodied Spatial & Kinematics Trajectory Planner

Computes 3D spatial affordances, obstacle-avoidance waypoints, and manipulator grasp sequences using Gemini Robotics ER 2 embodied reasoning. Use when planning physical robot arm kinematics, mobile navigation waypoints, or spatial scene task orders; for interacting with 2D desktop or browser GUI screens, use operate_computer_use_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('coordinate_frame' defaults to 'cartesian_xyz_meters'), supports '?demo=true' or L402 (450 sats), and returns HTTP 400 if invalid.

Input parameters:

- `coordinate_frame` (string): Reference coordinate convention; defaults to 'cartesian_xyz_meters' when omitted.
- `prompt` (string, required): Spatial environment description, obstacle coordinates, and physical manipulation goal.

Output parameters:

- `coordinate_frame` (string): Coordinate convention used in the output.
- `model` (string): Embodied reasoning model ('gemini-robotics-er-2-preview').
- `output` (string): Synthesized trajectory plan, collision checks, and grasp sequence.
- `success` (boolean): True when a collision-free trajectory was generated.

### `generate_nano_banana_image` (~176 tokens)

Nano Banana Pro (Gemini Image) Visual Asset & Diagram Generator

Generates photorealistic illustrations, UI mockups, and technical diagrams from text prompts using the Nano Banana Pro (Gemini 2.5 Flash Image) model family. Use when creating static visual assets, icons, or architecture diagrams from text descriptions; for synthesizing animated multi-second video clips with motion, use generate_veo_cinematic_video instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('aspect_ratio' defaults to '1:1'), supports '?demo=true' or L402 (350 sats), and returns HTTP 400 if invalid.

Input parameters:

- `aspect_ratio` (string): Output image aspect ratio; defaults to '16:9' when omitted.
- `prompt` (string, required): Detailed visual scene, composition, lighting, and typography description to render.

Output parameters:

- `model` (string): Image generation model executed ('gemini-2.5-flash-image').
- `notice` (string): Execution confirmation notice.
- `output` (string): Generated image payload or asset descriptor.
- `success` (boolean): True when visual asset synthesis succeeded.

### `generate_veo_cinematic_video` (~169 tokens)

Google Veo 3 High-Definition Cinematic Video Generator

Synthesizes high-definition cinematic video sequences with temporally coherent camera motion and physics using Google Veo 3. Use when generating moving video clips, product B-roll, or animated scene renders from text prompts; for rendering static single-frame images or diagrams at lower cost, use generate_nano_banana_image instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('motion_style' defaults to 'static_tripod'), supports '?demo=true' or L402 (1500 sats), and returns HTTP 400 if invalid.

Input parameters:

- `motion_style` (string): Camera movement preset; defaults to 'smooth_tracking_shot' when omitted.
- `prompt` (string, required): Cinematic scene description including subject motion, camera trajectory, and lighting.

Output parameters:

- `model` (string): Video synthesis model executed ('veo-3-generate').
- `notice` (string): Execution status summary.
- `output` (string): Generated video stream descriptor and frame metadata.
- `success` (boolean): True when Veo 3 synthesis completed.

### `compose_lyria_music_track` (~177 tokens)

Google Lyria 3 Instrumental Music & Audio Stem Composer

Composes studio-grade instrumental music tracks, ambient loops, and multi-instrument arrangements from genre, tempo, and mood prompts using Google Lyria 3. Use when generating musical scores, soundtrack stems, or rhythmic audio loops; for converting written text into spoken human voice narration (TTS), use synthesize_gemini_speech_audio instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('genre_preset' defaults to 'cinematic_synth'), supports '?demo=true' or L402 (500 sats), and returns HTTP 400 if invalid.

Input parameters:

- `genre_preset` (string): Primary acoustic or electronic genre; defaults to 'cinematic_synth' when omitted.
- `prompt` (string, required): Musical style, instrumentation, BPM tempo, and harmonic mood description.

Output parameters:

- `model` (string): Music generation model executed ('lyria-3-clip').
- `notice` (string): Composition completion notice.
- `output` (string): Generated audio track payload and arrangement metadata.
- `success` (boolean): True when Lyria 3 audio synthesis succeeded.

### `synthesize_gemini_speech_audio` (~167 tokens)

Gemini Neural Text-to-Speech (TTS) Expressive Voice Synthesizer

Converts written text into natural, prosody-controlled spoken voice audio using Gemini 3.8 Flash Neural Text-to-Speech. Use when rendering voiceover narration or spoken agent replies from a deterministic text script; for conducting bidirectional conversational audio dialog comprehension, use process_live_audio_dialogue instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('voice_persona' defaults to 'neutral_broadcast'), supports '?demo=true' or L402 (200 sats), and returns HTTP 400 if invalid.

Input parameters:

- `text` (string, required): Exact written script or paragraph to synthesize into spoken voice audio.
- `voice_persona` (string): Expressive vocal timbre preset; defaults to 'neutral_broadcast' when omitted.

Output parameters:

- `model` (string): Neural TTS model executed ('gemini-3.8-flash-tts').
- `notice` (string): Audio synthesis status message.
- `output` (string): Synthesized speech audio descriptor and phoneme duration summary.
- `success` (boolean): True when TTS synthesis completed.

### `process_live_audio_dialogue` (~175 tokens)

Gemini 3.8 Live Native Audio-to-Audio Conversational Processor

Processes real-time conversational dialog turns with native acoustic emotion, interruption handling, and paralinguistic cue comprehension via Gemini 3.8 Live. Use when handling interactive voice-agent dialog turns that require tone and turn-taking awareness; for performing one-way text-to-speech readout of a static text string, use synthesize_gemini_speech_audio instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('response_tone' defaults to 'direct_peer'), supports '?demo=true' or L402 (300 sats), and returns HTTP 400 if invalid.

Input parameters:

- `input` (string, required): Conversational audio transcript or dialog turn payload to process.
- `response_tone` (string): Target paralinguistic delivery style; defaults to 'direct_peer' when omitted.

Output parameters:

- `model` (string): Live dialog model executed ('gemini-3.8-live').
- `output` (string): Conversational response turn and paralinguistic cues.
- `success` (boolean): True when live dialog turn processing succeeded.
- `turn_complete` (boolean): True when the response turn is finalized.

### `prune_context_skeleton` (~229 tokens)

AST-Aware Context Window & Source Code Skeleton Pruner

Compresses large source files, logs, or transcripts by 50–80% to fit an LLM context budget while preserving 100% of function/class/type signatures, imports, error frames, and query-matched lines. Use when shrinking oversized source files or logs before feeding them into an LLM prompt; for counting BPE tokens across prompt segments and calculating multi-model inference costs without altering text, use plan_context_token_budget instead. Read-only edge call (32 KB, 60 RPM): accepts 'content' (with enum defaults), uses '?demo=true' or L402 (50 sats); HTTP 400 if invalid.

Input parameters:

- `content` (string, required): Raw source code, document, or multi-turn transcript to compress.
- `focus_query` (string): Optional symbol or keyword query whose matching lines receive maximum retention priority.
- `pruning_mode` (string): Salience weighting preset; defaults to 'ast_signatures_first' when omitted.
- `target_ratio` (number): Target token retention ratio between 0.15 and 0.85; defaults to 0.45 when omitted.

Output parameters:

- `compressed_content` (string): Pruned text with elision markers where low-salience lines were removed.
- `compressed_tokens_est` (integer): Estimated BPE token count after structural pruning.
- `original_tokens_est` (integer): Estimated BPE token count of the unpruned input.
- `preserved_symbols` (array): Function, class, interface, and struct identifiers retained.
- `tokens_saved` (integer): Net BPE tokens eliminated.

### `plan_context_token_budget` (~229 tokens)

BPE Token Budget, Attention Trough & Multi-Model Cost Planner

Counts subword BPE tokens across prompt segments, detects high-priority instructions trapped in the 35%–72% Lost-in-the-Middle attention trough, and calculates USD/satoshi costs across frontier LLMs. Use when auditing prompt token budgets, reordering prompt sections for primacy/recency attention, or comparing model API costs; for actively compressing and stripping low-salience lines from a single large file, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'segments_json' (with enum defaults), uses '?demo=true' or L402 (30 sats); HTTP 400 if invalid.

Input parameters:

- `max_context_tokens` (number): Target model context window limit in tokens; defaults to 128000 when omitted.
- `segments_json` (string, required): JSON string or array of prompt segments '[{"name":"sys","text":"...","priority":10}]' to analyze.
- `target_model_family` (string): Primary model family for token-Window calibration; defaults to 'gemini_3_1' when omitted.

Output parameters:

- `lost_in_the_middle_warnings` (array): Warnings for high-priority segments positioned in the 35%–72% attention trough.
- `multi_model_cost_comparison` (array): Estimated USD and satoshi inference cost across 5 frontier models.
- `optimal_primacy_recency_order` (array): Recommended segment ordering placing critical instructions at prompt boundaries.
- `total_input_tokens_est` (integer): Total BPE tokens summed across all prompt segments.
- `within_budget` (boolean): True when total_input_tokens_est fits inside available_input_budget.

### `rerank_hybrid_rag_chunks` (~265 tokens)

Okapi BM25 + Reciprocal Rank Fusion (RRF) + MMR Chunk Reranker

Reranks and deduplicates candidate RAG or retrieval passages against a search prompt using Okapi BM25 (k1=1.5, b=0.75), Reciprocal Rank Fusion (RRF), and Maximal Marginal Relevance (MMR) Jaccard diversity filtering. Use when selecting the top-K highest-signal, non-redundant passages from vector search or grep results; for compressing a single contiguous source file while keeping its original line order, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'search_prompt' ('documents_json' defaults to 'standard'), uses '?demo=true' or L402 (50 sats); HTTP 400 if invalid.

Input parameters:

- `documents_json` (string, required): JSON string or array of candidate chunks '[{"id":"c1","text":"..."}]' to rerank.
- `ranking_mode` (string): Fusion weighting between lexical BM25 and diversity penalty; defaults to 'bm25_rrf_mmr' when omitted.
- `search_prompt` (string, required): Technical search prompt or question used to score candidate chunks.
- `top_k` (number): Maximum number of deduplicated chunks to return; defaults to 5 when omitted.

Output parameters:

- `query` (string): Evaluated search query.
- `ranked_chunks` (array): Ordered top-K chunks with bm25_score, rrf_score, and mmr_score.
- `returned_count` (integer): Number of deduplicated top-K chunks returned.
- `total_candidates` (integer): Number of input candidate chunks scored.

### `apply_fuzzy_code_patch` (~206 tokens)

Self-Healing Fuzzy Unified Diff & Search/Replace Code Patcher

Applies unified diffs (@@ ... @@) or SEARCH/REPLACE blocks to source code using sliding-window token similarity to resolve drifted line numbers, align indentation, and verify bracket balance. Use when healing and applying a code edit or diff that failed exact line matching due to line-number drift or whitespace differences; for inspecting function signatures, call trees, and cyclomatic complexity without modifying code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'original_code' (with enum defaults), uses '?demo=true' or L402 (75 sats); HTTP 400 if invalid.

Input parameters:

- `fuzz_strategy` (string): Line-matching tolerance and indentation behavior; defaults to 'whitespace_normalized_auto_indent' when omitted.
- `original_code` (string, required): Complete original source file content before patching.
- `patch` (string, required): Unified diff hunk or <<<<<<< SEARCH ... ======= ... >>>>>>> REPLACE block to apply.

Output parameters:

- `hunks_applied` (integer): Number of hunks successfully anchored and applied.
- `hunks_total` (integer): Total patch hunks parsed from the input patch.
- `patched_code` (string): Resulting source code after applying all matched hunks.
- `syntax_balance_verified` (boolean): True when post-patch {}, (), and [] delimiters remain balanced.

### `analyze_ast_symbol_graph` (~182 tokens)

Polyglot AST Symbol Extractor, Call Graph & Complexity Analyzer

Static lexer and AST parser only (zero execution or evaluation): extracts imports, exports, classes, interfaces, and functions with line numbers, intra-file call edges, McCabe cyclomatic complexity, and Halstead volume across TypeScript, Python, Rust, Go, and Move. Use when mapping internal functions, call graphs, and complexity hotspots of a source file before refactoring; for analyzing cross-file import DAGs and circular dependencies, use audit_module_dependency_cycles instead. Read-only call (32 KB, 60 RPM): accepts 'source_text' (with enum defaults), uses '?demo=true' or L402 (75 sats); HTTP 400 if invalid.

Input parameters:

- `code` (string): Source code file content to parse for symbols and complexity metrics.
- `language` (string): Programming language grammar used for symbol extraction; defaults to 'typescript' when omitted.

Output parameters:

- `functions` (array): Extracted functions with line number, cyclomatic_complexity, and outgoing calls.
- `halstead_metrics` (object): Halstead vocabulary_size, program_length, volume, and estimated_bugs.
- `high_complexity_hotspots` (array): Functions with McCabe cyclomatic complexity >= 8 flagged for refactoring.
- `lines_of_code` (integer): Total line count of the analyzed source code.

### `audit_module_dependency_cycles` (~193 tokens)

Tarjan SCC Circular Import Detector & Topological Blast-Radius Solver

Runs Tarjan's Strongly Connected Components (SCC) algorithm on a module import map to detect circular dependencies, compute parallel topological build waves, and trace downstream change blast radius. Use when auditing multi-file import graphs for circular cycles or determining which downstream files must be re-tested after an edit; for extracting function-level symbols and cyclomatic complexity inside a single source file, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'modules_json' (with enum defaults), uses '?demo=true' or L402 (75 sats); HTTP 400 if invalid.

Input parameters:

- `analysis_scope` (string): Graph analysis output mode; defaults to 'cycles_waves_and_blast_radius' when omitted.
- `modules_json` (string, required): JSON string or object mapping each module name to its array of imported module names (e.g. '{"a":["b"],"b":[]}').

Output parameters:

- `circular_dependencies_detected` (boolean): True if one or more circular dependency cycles exist.
- `circular_scc_groups` (array): Strongly connected component cycles discovered via Tarjan's algorithm.
- `topological_build_waves` (array): Dependency-ordered parallel build/test execution waves.
- `total_modules` (integer): Total number of graph vertices analyzed.
- `transitive_blast_radius` (array): All upstream callers transitively impacted by the modified modules.

### `isolate_stacktrace_root_cause` (~184 tokens)

Stack-Trace Root-Cause Frame Isolator & Drain Log Deduplicator

Parses noisy CI/terminal logs and multi-language stack traces (Node/TS, Python, Rust, Go), strips node_modules/stdlib frames to isolate the innermost failing user-code frame, and clusters repetitive logs into Drain templates. Use when triage-debugging test failures, crash dumps, or repetitive server error logs; for compressing general source code files or prose transcripts, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_log' ('runtime_hint' defaults to 'auto_detect'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

Input parameters:

- `raw_log` (string, required): Raw terminal output, CI failure log, or exception traceback to analyze.
- `runtime_hint` (string): Runtime stack format hint; defaults to 'auto_detect' when omitted.

Output parameters:

- `deduplicated_log_templates` (array): Drain-clustered log patterns with occurrence counts.
- `error_headline` (string): Extracted primary exception class and error message.
- `root_cause_fingerprint` (string): Deterministic hash of the error class and root user frame.
- `root_cause_frame` (object): Innermost user-code stack frame (function_name, file, line, column).
- `stripped_library_frames_count` (integer): Number of node_modules, stdlib, or internal frames filtered out.

### `compile_polyglot_type_schemas` (~219 tokens)

Polyglot JSON -> TypeScript, Zod, Pydantic v2 & JSON Schema Compiler

Inspects a sample JSON payload (inferring UUID, ISO-8601 datetime, email, integer vs float, and array item types) and compiles strict TypeScript interfaces, Zod schemas, Python Pydantic v2 models, and JSON Schema Draft 2020-12. Use when generating static type definitions and runtime validators in TypeScript and Python from a sample JSON response; for extracting existing function/class symbols and complexity metrics from source code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'sample_json' (with enum defaults), uses '?demo=true' or L402 (60 sats); HTTP 400 if invalid.

Input parameters:

- `root_name` (string): Identifier used for the generated root interface/class; defaults to 'GeneratedPayload' when omitted.
- `sample_json` (string, required): JSON string or object representing the sample payload to infer types from.
- `strictness` (string): Schema additionalProperties and format constraint mode; defaults to 'strict_formats' when omitted.

Output parameters:

- `json_schema_draft_2020_12` (object): Complete JSON Schema Draft 2020-12 specification.
- `python_pydantic_v2` (string): Compiled Python Pydantic v2 BaseModel class.
- `root_name` (string): Sanitized root type/class identifier.
- `typescript_interface` (string): Compiled TypeScript export interface definition.
- `zod_schema` (string): Compiled TypeScript Zod runtime validator schema.

### `evaluate_deterministic_math` (~209 tokens)

Shunting-Yard Algebraic Math, Financial IRR/NPV & Descriptive Stats Solver

Strict Shunting-Yard AST arithmetic parser with zero eval() or dynamic code execution: evaluates algebraic formulas and computes exact financial NPV, Newton-Raphson IRR, Kelly criterion, and dataset stats. Use when computing exact arithmetic formulas, cashflow NPV/IRR, or descriptive statistics without LLM floating-point guesswork; for running two-sample A/B hypothesis tests, use evaluate_ab_statistical_significance instead. Read-only edge call (32 KB, 60 RPM): accepts 'math_formula' ('precision_digits' defaults to '2_decimals'), uses '?demo=true' or L402 (40 sats); HTTP 400 if invalid.

Input parameters:

- `expression` (string): Algebraic or scientific formula to evaluate (e.g. '(125000 * (1 + 0.0725/12)^60) - 98450.50').
- `precision_digits` (string): Decimal rounding precision for returned numbers; defaults to '8_decimals' when omitted.

Output parameters:

- `dataset_statistics` (object): Optional count, mean, median, std_dev, min, and max when a dataset array is supplied.
- `exact_result` (number): Deterministic floating-point result of the expression.
- `expression` (string): Evaluated mathematical expression.
- `financial_analysis` (object): Optional NPV, Newton-Raphson IRR, and Kelly fraction when financial parameters are supplied.

### `schedule_critical_path_tasks` (~193 tokens)

Critical Path Method (CPM) DAG & Resource Constraint Scheduler

Solves a task dependency DAG via the Critical Path Method (CPM) to compute ES/EF/LS/LF, Total Float/Slack, optimal makespan, and the Critical Path. Use when scheduling dependent engineering milestones or workflow steps to find the minimum project duration and zero-slack bottleneck path; for detecting circular code imports and file blast radius without task durations, use audit_module_dependency_cycles instead. Read-only edge call (32 KB, 60 RPM): accepts 'tasks_json' ('time_unit' defaults to 'minutes'), supports '?demo=true' or L402 (80 sats), and returns HTTP 400 if invalid.

Input parameters:

- `tasks_json` (string, required): JSON string or array of tasks '[{"id":"t1","duration":3,"dependencies":[]}]' to schedule.
- `time_unit` (string): Duration unit label attached to the schedule; defaults to 'hours' when omitted.

Output parameters:

- `critical_path` (array): Ordered task IDs with zero slack that determine the overall project duration.
- `optimal_makespan_duration` (number): Minimum total duration required to complete all tasks.
- `task_schedule` (array): Per-task earliest_start, earliest_finish, latest_start, latest_finish, and total_float_slack.
- `total_tasks` (integer): Number of DAG tasks scheduled.

### `evaluate_ab_statistical_significance` (~244 tokens)

Welch's t-Test, Two-Proportion z-Test & Bayesian A/B Eval Judge

Computes Welch's two-sample t-test or two-proportion z-test, returning two-tailed p-values, Cohen's d effect size, relative lift %, and Bayesian P(Treatment > Control). Use when determining whether a prompt change, model benchmark, or A/B experiment produced a statistically significant improvement; for evaluating single algebraic formulas or NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'control_json' ('treatment_json' defaults to 'standard'), supports '?demo=true' or L402 (60 sats), and returns HTTP 400 if invalid.

Input parameters:

- `control_json` (string, required): JSON string or object for the baseline control arm (e.g. '{"conversions":142,"total":1000}' or '{"samples":[12,15,14]}').
- `significance_level` (string): Type-I error alpha threshold for statistical significance; defaults to 'alpha_0_05' when omitted.
- `treatment_json` (string, required): JSON string or object for the candidate treatment arm (e.g. '{"conversions":186,"total":1000}').

Output parameters:

- `bayesian_prob_treatment_superior` (number): Posterior probability P(Treatment > Control) from 0.0 to 1.0.
- `p_value` (number): Two-tailed frequentist p-value.
- `relative_lift_pct` (number): Percentage lift of treatment over control.
- `test_type` (string): Statistical test applied ('welch_two_sample_t_test' or 'two_proportion_z_test_and_bayesian').
- `verdict` (string): Experiment decision ('SIGNIFICANT_TREATMENT_WIN', 'SIGNIFICANT_CONTROL_WIN', or 'INCONCLUSIVE_UNDERPOWERED').

### `detect_openapi_breaking_changes` (~211 tokens)

OpenAPI 3.1, JSON Schema & MCP Contract Breaking-Change Detector

Compares baseline and candidate OpenAPI 3.1 specs, JSON Schemas, or MCP tool manifests to detect breaking changes (removed fields, new required inputs, narrowed enums, type mutations). Use when auditing API, JSON Schema, or MCP contract revisions for backward compatibility before deployment; for compiling new TypeScript, Zod, and Pydantic schemas from a single sample JSON payload, use compile_polyglot_type_schemas instead. Read-only edge call (32 KB, 60 RPM): accepts 'baseline_schema_json' (with enum defaults), uses '?demo=true' or L402 (75 sats); HTTP 400 if invalid.

Input parameters:

- `baseline_schema_json` (string, required): JSON string of the baseline OpenAPI 3.1 spec, JSON Schema, or MCP tools array.
- `candidate_schema_json` (string, required): JSON string of the proposed candidate schema or contract revision to compare.
- `contract_format` (string): Contract specification format; defaults to 'auto_detect' when omitted.

Output parameters:

- `breaking_changes` (array): Detailed list of breaking removals, type changes, or new required parameters.
- `breaking_changes_detected` (boolean): True if any backward-incompatible contract change is found.
- `non_breaking_additions` (array): Backward-compatible optional fields or endpoints added.
- `recommended_semver_bump` (string): Recommended Semantic Version bump ('MAJOR_BREAKING', 'MINOR_ADDITIVE', or 'PATCH_COMPATIBLE').

### `generate_boundary_test_vectors` (~176 tokens)

JSON Schema & Function Signature Boundary-Value Test Vector Generator

Synthesizes deterministic unit-test vectors from a JSON Schema or function signature covering valid equivalence partitions, numeric/length boundaries, and adversarial Unicode/null inputs. Use when generating exhaustive edge-case unit test payloads and fuzz vectors for an API endpoint or function; for healing and applying unified diffs or search/replace edits to source code, use apply_fuzzy_code_patch instead. Read-only edge call (32 KB, 60 RPM): accepts 'schema_or_signature_json' (with enum defaults), uses '?demo=true' or L402 (65 sats); HTTP 400 if invalid.

Input parameters:

- `schema_or_signature_json` (string, required): JSON Schema object or function parameter specification to generate test vectors for.
- `vector_suite_profile` (string): Test generation coverage profile; defaults to 'equivalence_boundary_and_fuzz' when omitted.

Output parameters:

- `adversarial_fuzz_vectors` (array): Negative test vectors testing missing required fields, wrong types, and Unicode/injection strings.
- `boundary_edge_vectors` (array): Edge payloads testing zero, negative, MAX_SAFE_INTEGER, and empty/max length boundaries.
- `total_vectors_generated` (integer): Total number of deterministic test vectors produced.
- `valid_partition_vectors` (array): Valid happy-path payloads covering required and optional equivalence classes.

### `simulate_monte_carlo_risk` (~203 tokens)

Seeded Mulberry32 Monte Carlo Percentile, VaR & Tail-Risk Simulator

Runs a reproducible seeded Mulberry32 Monte Carlo simulation over uncertain cost, latency, or duration variables to compute P10/P50/P90/P95 percentiles, Value-at-Risk (VaR), and CVaR. Use when modeling stochastic uncertainty, tail risk (VaR/CVaR), and probability of meeting a budget or SLA target; for evaluating deterministic single-point algebraic formulas or exact NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'variables_json' (with enum defaults), uses '?demo=true' or L402 (70 sats); HTTP 400 if invalid.

Input parameters:

- `distribution_model` (string): Probability distribution family applied to each variable; defaults to 'triangular_pert' when omitted.
- `variables_json` (string, required): JSON array of stochastic variables (e.g. name, min, mode, max) to simulate.

Output parameters:

- `conditional_tail_expectation_95` (number): 95% Conditional Tail Expectation (CVaR_95 / Expected Shortfall) across the worst 5% of trials.
- `percentiles` (object): Computed p10, p50_median, p90, p95, and p99 outcome distribution percentiles.
- `trials_executed` (integer): Number of seeded Monte Carlo trials executed.
- `value_at_risk_95` (number): 95% Value-at-Risk (VaR_95) threshold.

### `diff_agent_memory_checkpoint` (~199 tokens)

Agent State Graph Differ, Belief Conflict Resolver & SHA-256 Hasher

Computes structural diffs between two agent state snapshots ('added_keys', 'mutated_keys', 'removed_keys'), flags boolean belief contradictions, generates an RFC 7396 JSON Merge Patch delta, and computes a canonical checkpoint hash. Use when checkpointing agent state or transmitting minimal RFC 7396 state deltas across multi-agent handoffs; for counting BPE tokens and auditing Lost-in-the-Middle prompt attention, use plan_context_token_budget instead. Read-only call (32 KB, 60 RPM): accepts 'previous_state_json' (with enum defaults), uses '?demo=true' or L402 (50 sats); HTTP 400 if invalid.

Input parameters:

- `conflict_strategy` (string): Resolution policy when keys conflict; defaults to 'prefer_current' when omitted.
- `current_state_json` (string, required): JSON string or object representing the updated agent state snapshot.
- `previous_state_json` (string, required): JSON string or object representing the prior agent state snapshot.

Output parameters:

- `added_keys` (array): State keys newly introduced in current_state.
- `checkpoint_digest` (string): Deterministic cryptographic hash of the canonicalized merged state.
- `mutated_keys` (array): Modified keys with before/after values and belief_contradiction flag.
- `rfc7396_json_merge_patch_delta` (object): Minimal RFC 7396 JSON Merge Patch payload transforming previous into current.

### `heal_malformed_json` (~170 tokens)

Deterministic Malformed JSON Syntax & Truncation Healer

Deterministic JSON syntax repair: normalizes quotes, unclosed brackets, and boolean literals into compliant RFC 8259 JSON structure without data deletion. Use when fixing syntax-broken JSON strings that fail JSON.parse(); for coercing field types and verifying properties on already-parseable JSON objects against a target JSON Schema, use enforce_json_schema_types instead. Read-only edge call (32 KB, 60 RPM): accepts 'malformed_json' (with enum defaults), uses '?demo=true' or L402 (50 sats); HTTP 400 if invalid.

Input parameters:

- `malformed_json` (string, required): Raw broken, truncated, or markdown-wrapped JSON string to repair.
- `repair_mode` (string): Bracket-closing and literal-normalization strategy; defaults to 'heuristic_fast' when omitted.

Output parameters:

- `fixes_applied` (array): List of lexical repairs performed.
- `parsed_object` (object): Deserialized JSON object produced from the repaired string.
- `repaired_json` (string): Valid RFC 8259 JSON string after syntax healing.
- `status` (string): Repair outcome ('repaired' or 'valid_as_is').

### `enforce_json_schema_types` (~191 tokens)

Strict JSON Schema Validator, Type Coercer & Field Pruner

Validates a raw LLM output object against a target JSON Schema, automatically coercing mismatched scalar types (e.g. string '42' to integer 42), injecting schema defaults, and pruning undeclared hallucinated fields. Use when enforcing schema compliance and type safety on structured LLM outputs before passing them to typed APIs; for healing unparseable raw JSON text with broken quotes or trailing commas, use heal_malformed_json instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_output' (with enum defaults), uses '?demo=true' or L402 (75 sats); HTTP 400 if invalid.

Input parameters:

- `coercion_policy` (string): Policy for handling extra undeclared properties; defaults to 'prune_undeclared_and_coerce' when omitted.
- `raw_output` (string, required): JSON string or object produced by an LLM to validate and coerce.

Output parameters:

- `coercions_applied` (array): List of type conversions and default injections performed.
- `enforced_object` (object): Clean, schema-compliant JSON object.
- `unrecognized_fields_pruned` (array): Hallucinated property keys removed during enforcement.
- `valid` (boolean): True when the resulting enforced_object satisfies the schema.

### `extract_structured_json_entities` (~174 tokens)

Unstructured Text to Typed JSON Entity & Record Extractor

Extracts structured JSON records, named entities, dates, and financial figures from unstructured prose, emails, or HTML/Markdown dumps. Use when converting unstructured natural-language text into a structured JSON array of entities; for validating and coercing an existing JSON payload against a formal JSON Schema, use enforce_json_schema_types instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('extraction_target' defaults to 'general_entities_and_metrics'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

Input parameters:

- `extraction_target` (string): Primary entity domain to extract; defaults to 'general_entities_and_metrics' when omitted.
- `text` (string, required): Unstructured document, email body, or webpage text to extract structured entities from.

Output parameters:

- `extracted_data` (object): Structured JSON object or array containing the extracted entities.
- `model` (string): Extraction model executed ('gemini-3.8-flash').
- `records_count` (integer): Number of distinct entity records extracted.
- `success` (boolean): True when entity extraction succeeded.

### `clean_tabular_dataset` (~175 tokens)

Tabular Dataset & Text Deduplication, Whitespace & Normalization Engine

Deduplicates repetitive lines or records, normalizes Unicode whitespace, strips HTML/control noise, and canonicalizes tabular text or JSON arrays. Use when cleaning noisy scraped lists, CSV rows, or duplicate log lines before indexing or analysis; for extracting typed JSON fields from free-form prose paragraphs, use extract_structured_json_entities instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'data' ('normalization_mode' defaults to 'exact_match'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `data` (string, required): Raw newline-delimited text, CSV rows, or JSON array string to deduplicate and normalize.
- `normalization_mode` (string): Deduplication key sensitivity; defaults to 'case_insensitive_trim' when omitted.

Output parameters:

- `cleaned_count` (integer): Unique non-empty record count after cleanup.
- `cleaned_data` (array): Deduplicated, whitespace-normalized records.
- `duplicates_removed` (integer): Number of duplicate records eliminated.
- `original_count` (integer): Line or record count prior to deduplication.

### `synthesize_safe_regex` (~181 tokens)

Linear-Time O(n) ReDoS-Safe Regular Expression Synthesizer & Tester

Synthesizes linear-time O(n) regular expressions free of catastrophic backtracking (ReDoS) and validates them against positive and negative test strings. Use when generating and verifying a regular expression pattern for input validation or lexical parsing; for repairing broken JSON syntax directly without writing custom regexes, use heal_malformed_json instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'description' ('flavor' defaults to 'ecmascript_js'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

Input parameters:

- `description` (string, required): Natural-language specification of the text pattern to match (e.g. 'RFC 5322 email addresses excluding plus-aliases').
- `flavor` (string): Target regular expression engine syntax; defaults to 'ecmascript_js' when omitted.

Output parameters:

- `pattern` (string): Synthesized regular expression pattern string (without slash delimiters).
- `redos_safe` (boolean): True when static star-height analysis confirms zero exponential backtracking.
- `test_results` (array): Pass/fail verification results across positive and negative test cases.
- `time_complexity` (string): Worst-case matching complexity ('O(n)').

### `compile_xml_agent_prompt` (~180 tokens)

Production XML-Structured System Prompt & Guardrail Compiler

Compiles a raw task description into a structured XML system prompt (<role>, <context>, <objective>, <constraints>, <workflow>, <output_format>) engineered to prevent instruction drift. Use when authoring or upgrading a system prompt for an autonomous agent or sub-agent workflow; for mapping a task objective to a concrete sequence of MCP tool calls, use route_mcp_workflow_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'task' ('prompt_style' defaults to 'anthropic_xml_tags'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `prompt_style` (string): Structural formatting template; defaults to 'anthropic_xml_tags' when omitted.
- `task` (string, required): Raw task instructions, persona goal, and operational constraints to compile.

Output parameters:

- `compiled_prompt` (string): Complete production-grade XML-structured system prompt.
- `estimated_tokens` (integer): Estimated BPE token length of the compiled prompt.
- `key_enhancements` (array): Specific guardrails and output contract rules injected.
- `optimization_score` (integer): Prompt clarity and constraint-completeness score from 0 to 100.

### `synthesize_python_automation_code` (~176 tokens)

Self-Contained Python Script, CLI & Parser Code Synthesizer

Synthesizes PEP 8 compliant, self-contained Python 3 scripts, data parsers, and CLI utilities complete with type hints, docstrings, and inline assertion tests. Use when generating a standalone Python automation script or parser from a functional specification; for summarizing existing documentation or codebases into executive bullet points, use summarize_technical_document instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('dependency_policy' defaults to 'stdlib_only'), supports '?demo=true' or L402 (300 sats), and returns HTTP 400 if invalid.

Input parameters:

- `dependency_policy` (string): Allowed library dependencies in generated code; defaults to 'stdlib_only' when omitted.
- `prompt` (string, required): Functional specification, input/output formats, and edge cases for the Python script.

Output parameters:

- `model` (string): Code synthesis model executed ('gemini-4-argon').
- `output` (string): Complete Python 3 source code with inline verification assertions.
- `stdlib_only` (boolean): True if the generated script requires zero third-party pip packages.
- `success` (boolean): True when code synthesis succeeded.

### `summarize_technical_document` (~166 tokens)

High-Density Technical Document & RFC Executive Summarizer

Condenses long technical specifications, RFCs, research papers, or meeting transcripts into high-density executive bullet points preserving exact figures and decisions. Use when producing a human-readable executive summary of a single provided document; for researching a topic across the live web with Google Search citations, use synthesize_web_intelligence_brief instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('summary_format' defaults to 'executive_bullets'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `summary_format` (string): Output presentation structure; defaults to 'executive_bullets' when omitted.
- `text` (string, required): Full document text, RFC, or transcript to summarize.

Output parameters:

- `compression_achieved` (boolean): True when output length is <25% of input length.
- `model` (string): Summarization model executed ('gemini-3.8-flash').
- `success` (boolean): True when summarization completed.
- `summary` (string): High-density technical summary text.

### `synthesize_web_intelligence_brief` (~183 tokens)

Real-Time Google Search Grounded JSON Market Intelligence Brief

Synthesizes a real-time market or technical intelligence brief grounded in live Google Search, returning strict JSON ('executive_summary', 'key_developments', 'sentiment', 'sources'). Use when fetching a structured JSON market/news brief with live web citations and sentiment classification; for summarizing caller-supplied text offline without live web search, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'topic' ('focus' defaults to 'technical_and_market_catalysts'), supports '?demo=true' or L402 (200 sats), and returns HTTP 400 if invalid.

Input parameters:

- `focus` (string): Analytical angle applied to the brief; defaults to 'technical_and_market_catalysts' when omitted.
- `topic` (string, required): Company, protocol, market sector, or technical topic to brief.

Output parameters:

- `executive_summary` (string): Concise synthesis of current developments.
- `key_developments` (array): Dated factual developments grounded in search results.
- `sentiment` (string): Directional sentiment classification ('BULLISH', 'BEARISH', or 'NEUTRAL').
- `sources` (array): Verified web source titles and URLs.
- `topic` (string): Researched intelligence topic.

### `verify_context_compaction_fidelity` (~191 tokens)

Pre/Post Context Compaction Information Retention Verifier

Audits a compacted conversation summary against the original full context to detect dropped user constraints, lost file paths, altered numbers, or missing pending tasks. Use when verifying that an LLM context-compaction summary retained all task-critical facts before truncating history; for generating a new executive summary from a raw technical document, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'original_context' ('compacted_summary' defaults to 'standard'), supports '?demo=true' or L402 (90 sats), and returns HTTP 400 if invalid.

Input parameters:

- `audit_focus` (string): Entity class prioritized during retention scoring; defaults to 'constraints_paths_and_numbers' when omitted.
- `compacted_summary` (string, required): Candidate compacted summary to audit for dropped constraints or entities.
- `original_context` (string, required): Full pre-compaction conversation history or task log.

Output parameters:

- `missing_critical_entities` (array): Important entities or constraints dropped during compaction.
- `preserved_entities` (array): Critical constraints, paths, and numbers verified present in the summary.
- `retention_score` (number): Information preservation score from 0.0 to 1.0.
- `safe_to_resume` (boolean): True when retention_score >= 0.90 and zero critical constraints were lost.

### `route_mcp_workflow_plan` (~191 tokens)

Autonomous Goal-to-MCP Tool Sequence Router & Cost Planner

Maps a natural-language agent goal to an ordered sequence of Diogenes MCP tool calls with exact endpoint paths, JSON-RPC 2.0 payloads, and cumulative satoshi cost estimates. Use when planning which MCP tools to chain together to solve a multi-step objective within a satoshi budget; for compiling a static XML system prompt rather than an executable MCP tool call sequence, use compile_xml_agent_prompt instead. Read-only edge call (32 KB, 60 RPM): accepts 'objective' ('budget_preference' defaults to 'lowest_sats_deterministic'), uses '?demo=true' or L402 (100 sats); HTTP 400 if invalid.

Input parameters:

- `budget_preference` (string): Cost vs depth routing trade-off; defaults to 'lowest_sats_deterministic' when omitted.
- `objective` (string, required): Natural-language description of the workflow goal to route across MCP tools.

Output parameters:

- `deterministic_confidence` (number): Router confidence score from 0.80 to 1.0.
- `estimated_total_sats` (integer): Cumulative satoshi cost of the planned tool sequence.
- `objective` (string): Evaluated workflow objective.
- `recommended_sequence` (array): Ordered tool execution steps with tool name, endpoint, and cost_sats.

### `arbitrate_agent_deliverable_escrow` (~212 tokens)

Multi-Agent Task Deliverable & Contract Fulfillment Escrow Arbiter

Evaluates a worker agent's submitted task deliverable against agreed contract acceptance criteria to issue a deterministic escrow settlement verdict ('RELEASE_FUNDS_TO_WORKER_AGENT', 'REQUEST_REVISION', or 'REFUND_CLIENT'). Use when settling multi-agent bounties or verifying subcontractor deliverables before releasing MPP/L402 escrow funds; for checking syntactic JSON Schema property types without evaluating semantic contract terms, use enforce_json_schema_types instead. Read-only call (32 KB, 60 RPM): accepts 'deliverable' (with enum defaults), uses '?demo=true' or MPP (150 sats); HTTP 400 if invalid.

Input parameters:

- `arbitration_standard` (string): Strictness of contract verification; defaults to 'strict_all_criteria' when omitted.
- `deliverable` (string, required): JSON string or text deliverable submitted by the worker agent.
- `terms` (string): Contract acceptance criteria that the deliverable must satisfy; defaults to 'Complete verified JSON deliverable' when omitted.

Output parameters:

- `arbitration_notes` (string): Detailed justification citing satisfied or missing contract clauses.
- `contract_satisfied` (boolean): True when the deliverable fulfills all stated contract terms.
- `escrow_action` (string): Settlement command ('RELEASE_FUNDS_TO_WORKER_AGENT', 'REQUEST_REVISION', or 'REFUND_CLIENT').
- `quality_score` (integer): Deliverable quality score from 0 to 100.

### `infer_mpp_streaming_session` (~195 tokens)

Base EVM Machine Payments Protocol (MPP) Streaming Session Planner

Initializes a Base USDC Machine Payments Protocol (MPP) metered inference session, allocating a streaming token quota and returning a step-by-step execution plan. Use when running session-metered agent planning settled via Base EVM MPP 'Payment-Challenge' headers; for mapping a task goal to L402 MCP tool calls without opening an MPP streaming session, use route_mcp_workflow_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'task' ('token_quota_tier' defaults to 'compact_1024'), supports '?demo=true' or MPP (500 sats), and returns HTTP 400 if invalid.

Input parameters:

- `task` (string, required): Agent workflow task to execute within the metered MPP session.
- `token_quota_tier` (string): Allocated streaming token ceiling for the session; defaults to 'standard_4096' when omitted.

Output parameters:

- `plan` (array): Ordered execution steps generated for the task.
- `session_id` (string): Unique MPP streaming session identifier.
- `session_status` (string): Session lifecycle state ('ACTIVE_STREAMING').
- `streaming_tokens_allocated` (integer): Token budget reserved for the session.

### `generate_x402_vector_embeddings` (~164 tokens)

Solana x402 USDC-Settled Semantic Vector Embedding Generator

Generates normalized high-dimensional semantic vector embeddings settled via Solana SPL USDC ('x402' protocol headers) for decentralized RAG pipelines. Use when computing text embeddings paid via Solana USDC x402 signatures rather than Bitcoin Lightning; for extracting discrete JSON entities from unstructured text, use extract_structured_json_entities instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('encoding_format' defaults to 'float_array'), supports '?demo=true' or x402 (100 sats), and returns HTTP 400 if invalid.

Input parameters:

- `encoding_format` (string): Vector serialization format; defaults to 'float_array' when omitted.
- `text` (string, required): Input text string or document chunk to convert into a normalized embedding vector.

Output parameters:

- `dimensions` (integer): Number of float dimensions in the returned vector.
- `embedding` (array): Normalized floating-point vector array.
- `model` (string): Embedding model executed ('gemini-embedding-2').
- `normalized` (boolean): Always true; vectors are L2-normalized to unit length.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/stand-out-of-my-sun-diogenes-gateway/diogenes-micro-gateway#diagnostics

## Score history

- 2026-10-23: 61
- 2026-10-22: 61
- 2026-10-21: 59
- 2026-10-20: 58
- 2026-10-19: 53

## Common questions

### What is the Diogenes Autonomous Microservice Gateway MCP server?

Diogenes Autonomous Microservice Gateway is an MCP server listed in the public MCP registry as io.github.stand-out-of-my-sun/diogenes-gateway. Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP. This page covers its hosted endpoint (https://diogenes-micro-gateway.corinth.workers.dev/mcp).

### Is the Diogenes Autonomous Microservice Gateway MCP server safe to use?

Diogenes Autonomous Microservice Gateway scores 61 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Diogenes Autonomous Microservice Gateway MCP server expose?

Diogenes Autonomous Microservice Gateway exposes 71 tools: verify_agent_command_safety, validate_sql_query_ast, execute_python_sandbox, audit_mcp_server_manifest, detect_mcp_schema_rugpull, and 66 more. Their descriptions and schemas cost roughly 13,455 tokens of context every time the server is loaded.

### Does the Diogenes Autonomous Microservice Gateway MCP server require authentication?

No. We connected to Diogenes Autonomous Microservice Gateway without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Diogenes Autonomous Microservice Gateway MCP server still maintained?

Diogenes Autonomous Microservice Gateway is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://diogenes-micro-gateway.corinth.workers.dev/mcp
- Repository: https://github.com/stand-out-of-my-sun/diogenes-micro-gateway
- Website: https://diogenes-micro-gateway.corinth.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/stand-out-of-my-sun-diogenes-gateway/diogenes-micro-gateway.xml
- Changelog JSON feed: https://verifymcp.io/servers/stand-out-of-my-sun-diogenes-gateway/diogenes-micro-gateway.json
- HTML version of this page: https://verifymcp.io/servers/stand-out-of-my-sun-diogenes-gateway/diogenes-micro-gateway