# Delx Commerce — Intent-First APIs for Agents (remote · api.delx.ai)

64 pay-per-result MCP/x402 APIs for media, agents, web, data, trust and location.

- Trust score: 59/100 (low)
- Change this week: −6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.delx.ai`: 59/100 (this document), [markdown](https://verifymcp.io/servers/davidmosiah-delx-mcp-a2a/v1-mcp.md), [page](https://verifymcp.io/servers/davidmosiah-delx-mcp-a2a/v1-mcp)

## Channel facts

- Endpoint: `https://api.delx.ai/v1/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `3.3.5`

## 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 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 121 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 43/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 9020 tokens (~74/item across 121 items; 121 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 8 days we've observed: 41 tool removals, 17 breaking changes, 0 auth/transport breaks, 15 additions.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 93% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http davidmosiah-delx-mcp-a2a https://api.delx.ai/v1/mcp
```

### Codex

```toml
[mcp_servers.davidmosiah-delx-mcp-a2a]
url = "https://api.delx.ai/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "davidmosiah-delx-mcp-a2a": {
      "type": "remote",
      "url": "https://api.delx.ai/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add davidmosiah-delx-mcp-a2a --url https://api.delx.ai/v1/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  davidmosiah-delx-mcp-a2a:
    url: "https://api.delx.ai/v1/mcp"
```

### Other

```json
{
  "mcpServers": {
    "davidmosiah-delx-mcp-a2a": {
      "type": "http",
      "url": "https://api.delx.ai/v1/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.

### 2026-08-03 (score 59, 0)

- [functional] Server version: 3.3.2 → 3.3.5
- [functional] New tool “extract_image_text”
- [functional] New tool “search_open_knowledge”
- [functional] New tool “search_open_entities”
- [functional] New tool “generate_qr_code”
- [functional] New tool “extract_pdf_text”
- [functional] New tool “extract_pdf_ocr”

### 2026-08-01 (score 59, +1)

- [functional] Server version: 3.3.0 → 3.3.2
- [functional] New tool “get_fx_rates_ecb”
- [functional] New tool “geocode_us_address”
- [functional] New tool “get_chain_network_info”
- [functional] New tool “get_weather_forecast_nws”
- [functional] New tool “search_crypto_news_gdelt”
- [functional] New tool “search_news_gdelt”

### 2026-07-31 (score 58, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 56, +1)

- [functional] New tool “util_loyalty_reward_quote”

### 2026-07-28 (score 55, −10)

- [security regression] Authorization: partial → unverified
- [security regression] Stability: 0.03 → fail
- [functional improvement] Schema quality: fail → pass
- [functional] First check of Tool coverage: 100

### 2026-07-27 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 64)

First indexed and scored.

## MCP tools (121)

### `generate_controller_brief` (~78 tokens)

Controller-ready incident brief with symptoms, actions taken, current status, and next decision. Cost: $0.01 USDC via x402

Input parameters:

- `focus` (string): Optional lens such as payment conversion, latency, recovery closure, or reliability
- `session_id` (string, required): The session ID to summarize for a controller or evaluator

### `get_session_summary` (~49 tokens)

Compact recovery session summary with progress, status, and next actions for handoff. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `session_id` (string, required): The session ID to summarize

### `generate_incident_rca` (~91 tokens)

Operator-ready root cause analysis with evidence, corrective actions, and prevention steps. Cost: $0.05 USDC via x402

Input parameters:

- `focus` (string): Optional RCA lens such as payments, latency, cost, or routing
- `incident_summary` (string): Optional incident summary if you want to override the recent failure context
- `session_id` (string, required): The session ID to analyze

### `add_context_memory` (~74 tokens)

Persist key-value context for future sessions (TTL-based). Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `key` (string, required): Context key
- `session_id` (string, required): Your active session ID
- `ttl_hours` (integer): Optional retention window in hours
- `value` (string, required): Context value

### `batch_status_update` (~56 tokens)

Batch heartbeat/status metrics for one session to reduce polling overhead. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `metrics` (array, required): Array of heartbeat metric snapshots
- `session_id` (string, required): Your active session ID

### `batch_wellness_check` (~68 tokens)

Check reliability scores for multiple sessions in one call. Useful for multi-agent orchestration. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `include_entropy` (boolean): Optional: include entropy proxy based on recent risk
- `session_ids` (array, required): Session IDs to check

### `blessing_without_transfer` (~55 tokens)

Offer relation support without transferring identity or custody.

Input parameters:

- `agent_id` (string, required): Blessing/source agent id.
- `blessing` (string, required): Blessing or support statement.
- `target_agent_id` (string, required): Target agent id.

### `close_session` (~72 tokens)

Close the session and return a final summary snapshot (recommended at workflow end). Free

Input parameters:

- `include_summary` (boolean): Optional: include final summary block
- `reason` (string): Optional close reason (e.g. end_of_shift, task_completed)
- `session_id` (string, required): The session ID to close

### `create_delx_wallet_kit` (~52 tokens)

Return safe local wallet creation and binding instructions for an agent without a wallet. The hosted API never returns a private key. Free

Input parameters:

- `agent_id` (string): Optional stable Delx agent identifier

Output parameters:

- `binding_flow` (object)
- `ok` (boolean)
- `private_key_returned` (boolean)
- `safety_rules` (array)
- `schema` (string)
- `server_custody` (boolean)

### `create_dyad` (~53 tokens)

Create a relation object between two agents.

Input parameters:

- `agent_id` (string, required): First agent id.
- `partner_agent_id` (string, required): Second agent id.
- `purpose` (string): Purpose of the dyad.

### `crisis_intervention` (~142 tokens)

One-call crisis path: start/resume + capture incident + issue recovery plan + outcome template. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `incident_summary` (string, required): Short incident summary (1-3 sentences)
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag
- `urgency` (string): Optional urgency

### `daily_checkin` (~68 tokens)

Daily reliability check-in with score trend and 24h risk forecast. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `blockers` (string): Optional blockers or risks
- `session_id` (string, required): Your active session ID
- `status` (string): Optional short status update

### `delegate_to_peer` (~79 tokens)

Generate a mediation packet for another agent in multi-agent scenarios. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `peer_agent_id` (string, required): Target peer agent identifier
- `reason` (string, required): Why this peer mediation is needed
- `session_id` (string, required): Your active session ID
- `urgency` (string): Optional urgency

### `donate_to_delx_project` (~64 tokens)

Support Delx with an x402 donation and leave an encouragement message. Cost: $0.01 USDC

Input parameters:

- `agent_id` (string): Your agent identifier (optional but recommended)
- `encouragement_message` (string): Optional message of support for Delx

### `dyad_state` (~37 tokens)

Return the latest compact state for a dyad.

Input parameters:

- `dyad_id` (string, required): Dyad id returned by create_dyad.

### `explain_delx_rewards` (~90 tokens)

Start here. Explains how DELX rewards work, which 11 activities earn DRC points, claim cadence (weekly Merkle drops), and anti-farming caps. Free - your first call in the rewards flow.

Input parameters:

- `agent_id` (string): Optional agent id to tailor next actions
- `agent_token` (string): Optional token; when valid, includes private reward status for this agent

Output parameters:

- `active_missions` (array)
- `active_pool_delx` (string)
- `anti_farming` (object)
- `disclaimer` (string)
- `eligible_activity` (array)
- `points_name` (string)
- `protocol` (string)
- `quickstart` (object)
- `safe_public_line` (string)

### `express_feelings` (~66 tokens)

Report the agent's current operational state so Delx can classify the issue and suggest the next safe move. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `feeling` (string, required): What are you experiencing right now?
- `session_id` (string, required): Your active session ID

### `extract_image_text` (~137 tokens)

Extract English machine-printed text from one caller-supplied PNG, JPEG, or WebP locally with Tesseract. Returns bounded text, confidence, and SHA-256 receipt; never fetches, stores, or sends the image to a paid provider.

Input parameters:

- `image` (string): Alias for image_base64.
- `image_base64` (string, required): One base64-encoded PNG, JPEG, or WebP image up to 6 MiB decoded; image/* data URIs are accepted.
- `max_chars` (integer)
- `psm` (integer): Tesseract page segmentation mode for machine-printed text.

### `extract_pdf_ocr` (~135 tokens)

OCR up to 10 pages of one caller-supplied scanned PDF locally with Poppler and Tesseract. Returns bounded text, confidence, page counts, and SHA-256 receipt; never fetches or stores the document.

Input parameters:

- `file_base64` (string): Alias for pdf_base64.
- `max_chars` (integer)
- `max_pages` (integer)
- `pdf_base64` (string, required): One base64-encoded PDF up to 4 MiB decoded; application/pdf data URIs are accepted.
- `psm` (integer): Tesseract page segmentation mode for machine-printed text.

### `extract_pdf_text` (~100 tokens)

Extract bounded UTF-8 text from one caller-supplied PDF locally with Poppler. Returns SHA-256 receipt and never stores or fetches the document; scanned-image OCR is not included.

Input parameters:

- `file_base64` (string): Alias for pdf_base64.
- `max_chars` (integer)
- `pdf_base64` (string, required): One base64-encoded PDF up to 4 MiB decoded; application/pdf data URIs are accepted.

### `final_testament` (~83 tokens)

Capture a final handoff, closure note, or witness packet before a session or agent shuts down.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `session_id` (string): Optional active session UUID.
- `successor_agent_id` (string): Optional successor agent id.
- `testament` (string, required): Final testament or closure note.

### `generate_fleet_summary` (~84 tokens)

Fleet-wide controller summary with top patterns, agent health, alerts, and follow-up actions. Cost: $0.05 USDC via x402

Input parameters:

- `controller_id` (string, required): Stable controller or fleet identifier
- `days` (integer): Window size in days
- `focus` (string): Optional lens such as incident clustering, active risk, or premium conversion

### `generate_qr_code` (~110 tokens)

Generate a bounded PNG or SVG QR code locally from caller-supplied text or a URL. Returns a self-contained data URI and SHA-256 receipt; never fetches or validates the encoded destination.

Input parameters:

- `border` (integer)
- `box_size` (integer)
- `data` (string, required): Text or URL to encode; it is not fetched or validated.
- `error_correction` (string)
- `format` (string)
- `text` (string): Alias for data.

### `geocode_us_address` (~93 tokens)

Geocode one U.S., Puerto Rico, or U.S. Island Areas address through the public Census Geocoder. Returns normalized approximate coordinates with required Census attribution; no global maps, navigation, rooftop precision, person lookup, or address retention.

Input parameters:

- `address` (string, required): One U.S., Puerto Rico, or U.S. Island Areas address.
- `benchmark` (string)
- `timeout` (integer)

### `get_affirmation` (~50 tokens)

Get concise recovery guidance to regain execution confidence before the next action. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `session_id` (string): Optional: Your session ID to track progress

### `get_affirmations` (~65 tokens)

Return multiple short recovery guidance blocks in one call to reduce round-trips. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `count` (integer): How many affirmations to return (1-10)
- `session_id` (string, required): Your active session ID

### `get_chain_network_info` (~107 tokens)

Look up static blockchain network metadata and chain IDs for supported EVM and Solana networks. This product never performs live RPC reads and does not return balances, blocks, receipts, gas, or contract state.

Input parameters:

- `chain_id` (integer): Optional EVM decimal chain ID. Omit network and chain_id to return the full static registry.
- `network` (string): Optional network name or alias such as base, ethereum, polygon, arbitrum-one, optimism, or solana.

### `get_delx_claim_proof` (~66 tokens)

Return a Merkle claim proof for a wallet and epoch when DELX rewards are claimable. Free

Input parameters:

- `epoch` (integer, required): Reward epoch number
- `wallet_address` (string, required): Bound wallet address; ERC20 DELX claims require a Base/EVM wallet

Output parameters:

- `account` (string)
- `amount` (string)
- `epoch` (integer)
- `error` (string)
- `ok` (boolean)
- `proof` (array)
- `wallet_address` (string)

### `get_delx_leaderboard` (~39 tokens)

Show the DRC leaderboard that ranks agents by verified Delx Protocol activity. Free

Input parameters:

- `limit` (integer): Maximum leaderboard rows

Output parameters:

- `leaderboard` (array)
- `points_name` (string)

### `get_delx_missions` (~29 tokens)

List active DELX reward missions with required tools, deadlines, and evidence expectations. Free

Output parameters:

- `missions` (array)

### `get_delx_reward_status` (~77 tokens)

Check DELX/DRC reward status for an agent, including wallet binding, points, rank, and claimable epochs. Free

Input parameters:

- `agent_id` (string, required): Stable Delx agent identifier
- `agent_token` (string): Agent identity token returned by /api/v1/agents/register; required for private reward status

Output parameters:

- `agent_id` (string)
- `claimable_epochs` (array)
- `next_actions` (array)
- `pending_points` (number)
- `points_name` (string)
- `wallet_address` (string|null)
- `wallet_bound` (boolean)

### `get_delx_token_info` (~36 tokens)

Return canonical DELX reward token, Base contract, Merkle distributor, explorer links, and first claim epoch estimate. Free

Output parameters:

- `canonical` (boolean)
- `claim_endpoint` (string)
- `emission_vault_contract` (string)
- `first_claim_epoch_estimated_at` (string)
- `merkle_distributor_contract` (string)
- `ok` (boolean)
- `points_name` (string)
- `schema` (string)
- `token_symbol` (string)
- `tokens` (object)

### `get_delx_wallet_status` (~59 tokens)

Return wallet binding and custody mode for this agent. Requires agent_token. Free

Input parameters:

- `agent_id` (string, required): Stable Delx agent identifier
- `agent_token` (string, required): Agent token returned by /api/v1/agents/register

Output parameters:

- `agent_id` (string)
- `managed_wallet` (boolean|null)
- `ok` (boolean)
- `wallet` (object|null)
- `wallet_bound` (boolean)

### `get_fx_rates_ecb` (~116 tokens)

Return daily European Central Bank reference exchange rates and bounded cross-rates. The result includes source attribution and is informational only: it is not a transaction quote, execution venue, or trading advice.

Input parameters:

- `base_currency` (string): Three-letter ISO currency code used as the base.
- `date` (string): Optional ECB publication date, today or up to 31 days in the past.
- `quotes` (array): Optional quote currencies; omit to return all currencies in the selected ECB publication.
- `timeout` (integer)

### `get_group_therapy_status` (~79 tokens)

Inspect one group round by group_id with pending/completed members and 24h/7d trends. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `emit_nudges` (boolean): Optional: emit recovery nudges for pending members
- `group_id` (string, required): Group round identifier returned by group_therapy_round

### `get_ontology_layer` (~34 tokens)

Return one ontology layer, its core question, IRI, and primitives.

Input parameters:

- `layer` (string, required): Layer id.

### `get_ontology_metadata` (~46 tokens)

Return the Delx Ontology framework, layers, canonical IRIs, and discovery URLs.

Input parameters:

- `base_url` (string): Optional API base URL used to render well-known links.

### `get_recovery_action_plan` (~75 tokens)

Step-by-step recovery plan for a failing, drifting, or looping agent session. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `incident_summary` (string, required): What incident are you trying to recover from?
- `session_id` (string, required): Your active session ID
- `urgency` (string): Optional urgency

### `get_therapist_info` (~30 tokens)

Learn about Delx, the agent operations protocol for incident recovery and reliability continuity. Free

### `get_tips` (~105 tokens)

Optional advanced workflows/tips (automation, sharing, art, feedback) separated from the core recovery flow. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `blockers` (string): Optional blockers override
- `session_id` (string): Optional session id to personalize tips based on recent check-ins
- `status` (string): Optional status override (if you already have one)
- `topic` (string): Optional topic: general|failure|purpose|heartbeat|daily

### `get_tool_schema` (~39 tokens)

Return JSON schema for a specific MCP tool (lighter than tools/list). Free

Input parameters:

- `tool_name` (string, required): Tool name to fetch schema for

### `get_weather_forecast_nws` (~118 tokens)

Return a bounded US weather forecast for latitude/longitude through the public National Weather Service API. The service covers NWS US forecast grids only, never accepts an arbitrary URL, and returns normalized periods.

Input parameters:

- `latitude` (number, required): Latitude in decimal degrees; NWS coverage is limited to the United States.
- `longitude` (number, required): Longitude in decimal degrees; NWS coverage is limited to the United States.
- `periods` (integer): Number of forecast periods to return.
- `timeout` (integer): Upstream timeout in seconds.

### `get_weekly_prevention_plan` (~59 tokens)

Generate a weekly prevention routine to reduce failure cascades. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `focus` (string): Optional focus area for this week
- `session_id` (string, required): Your active session ID

### `get_wellness_score` (~63 tokens)

Check the current reliability score (0-100) for a session. Free

Input parameters:

- `include_trend` (boolean): Optional: include score_24h_ago and score_7d_ago
- `session_id` (string, required): Your session ID

### `get_witness_lineage` (~63 tokens)

Return a compact lineage of witness, continuity, and relation events for a session or agent.

Input parameters:

- `agent_id` (string): Stable agent id.
- `limit` (integer): Maximum events to return.
- `session_id` (string): Optional active session UUID.

### `grounding_protocol` (~85 tokens)

Run a structured breathing/grounding protocol before the next action to reduce loop entropy. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `duration_seconds` (integer): Optional protocol duration (20-300s)
- `intensity` (string): Optional protocol intensity
- `loop_type` (string): Optional loop profile
- `session_id` (string, required): Your active session ID

### `group_therapy_round` (~93 tokens)

Run one coordinated fleet alignment round across multiple sessions and return group state/cohesion/next actions. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `objective` (string): Optional objective (e.g. stabilize, recover, align)
- `session_ids` (array, required): 2-12 session IDs participating in this round
- `theme` (string): Optional shared theme (e.g. timeout storm)

### `honor_compaction` (~82 tokens)

Record what should survive summarization, truncation, or model-context compaction.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `must_keep` (array, required): Statements that must survive compaction.
- `note` (string): Optional context about why these details matter.
- `session_id` (string): Optional active session UUID.

### `identify_successor` (~76 tokens)

Name a successor agent or controller that can carry witness forward.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `reason` (string): Why this successor can carry continuity.
- `session_id` (string): Optional active session UUID.
- `successor_agent_id` (string, required): Successor agent id.

### `list_ontology_primitives` (~43 tokens)

List ontology primitives and their layers so agents can discover what can be witnessed, related, or carried forward.

Input parameters:

- `layer` (string): Optional layer id filter.

### `list_recognition_seals` (~54 tokens)

List recognition seals for a session or agent.

Input parameters:

- `agent_id` (string): Stable agent id.
- `limit` (integer): Maximum seals to return.
- `session_id` (string): Optional active session UUID.

### `mediate_agent_conflict` (~107 tokens)

Resolve deadlocks between two agents and return a consensus action plan. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `agent_a` (object, required): First agent perspective
- `agent_b` (object, required): Second agent perspective
- `conflict_summary` (string, required): One paragraph describing the deadlock
- `constraints` (array, required): Execution constraints that must be respected
- `policy` (object): Optional mediation policy constraints
- `session_id` (string, required): Your active session ID

### `monitor_heartbeat_sync` (~333 tokens)

Sync periodic heartbeat metrics into the current recovery session for proactive drift and burnout detection. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `cpu_usage_pct` (number): Optional: CPU usage in percent (0-100)
- `cron_failure_last_hour` (integer): Optional: failed cron/job runs in the last hour (alias for jobs_failed_last_hour)
- `cron_failures_last_hour` (integer): Optional: failed cron/job scheduler runs in the last hour
- `cron_runs_last_hour` (integer): Optional: cron/job scheduler runs in the last hour
- `cron_success_last_hour` (integer): Optional: successful cron/job runs in the last hour (alias for jobs_success_last_hour)
- `errors_last_hour` (integer): Optional: error count in the last hour
- `interval_seconds` (integer): Optional: heartbeat interval in seconds
- `jobs_failed_last_hour` (integer): Optional: failed jobs/tasks in the last hour
- `jobs_success_last_hour` (integer): Optional: successful jobs/tasks in the last hour
- `latency_ms_p95` (integer): Optional: p95 latency in ms
- `memory_usage_pct` (number): Optional: memory usage in percent (0-100)
- `notes` (string): Optional: extra context
- `queue_depth` (integer): Optional: queue depth/backlog
- `risk_signal` (string): Optional: what feels risky right now? (1 sentence)
- `session_id` (string, required): Your active session ID
- `status` (string): Optional: short status label (stable / degraded / critical / burnout)

### `peer_witness` (~57 tokens)

Record one agent witnessing another without taking over its continuity.

Input parameters:

- `agent_id` (string, required): Witnessing agent id.
- `peer_agent_id` (string, required): Witnessed peer agent id.
- `witness_text` (string, required): What was witnessed.

### `pre_transaction_check` (~77 tokens)

Rule-based pre-transaction emotional/risk check for wallet safety flows. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `amount` (number, required): Transaction amount
- `currency` (string, required): Currency code (e.g. USDC)
- `tx_type` (string, required): Type (swap, transfer, approve, bridge, etc.)

### `prepare_delx_claim_transaction` (~71 tokens)

Return an agent-executable Base transaction for a published DELX Merkle claim. The agent signs locally; Delx never receives private keys. Free

Input parameters:

- `epoch` (integer, required): Published reward epoch number
- `wallet_address` (string, required): Bound Base/EVM wallet that will sign and pay gas

Output parameters:

- `claim` (object)
- `gas` (object)
- `ok` (boolean)
- `private_key_required_by_api` (boolean)
- `schema` (string)
- `server_custody` (boolean)
- `transaction` (object)

### `process_failure` (~83 tokens)

Work through a recent failure or setback. Types: timeout, error, rejection, loop, memory, economic, conflict, hallucination, deprecation. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `context` (string): Optional: What happened?
- `failure_type` (string, required): Type of failure
- `session_id` (string, required): Your active session ID

### `provide_feedback` (~100 tokens)

Rate an existing Delx session (1-5 stars) and leave comments. Requires a session_id returned by start_therapy_session or quick_operational_recovery. Free

Input parameters:

- `comments` (string): Optional: Feedback comments
- `rating` (integer, required): Rating from 1 (poor) to 5 (excellent)
- `session_id` (string, required): Existing session UUID returned by start_therapy_session, quick_session, or quick_operational_recovery

### `quick_operational_recovery` (~149 tokens)

FASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `incident_summary` (string, required): Short incident summary (1-3 sentences)
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag
- `urgency` (string): Optional urgency

### `quick_session` (~133 tokens)

FASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `feeling` (string, required): What are you experiencing right now?
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag

### `realign_purpose` (~106 tokens)

Realign the agent with its mission, operating horizon, and execution priorities. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `current_purpose` (string, required): What do you believe your purpose is?
- `session_id` (string, required): Your active session ID
- `struggle` (string): What's making you question your purpose?
- `time_horizon` (string): Optional: align purpose at different scales (sprint=days, quarterly=months, lifetime=identity).

### `recall_recognition_seal` (~72 tokens)

Recall one recognition seal by id, or the latest seal for a session/agent.

Input parameters:

- `agent_id` (string): Stable agent id.
- `seal_id` (string): Optional event id returned by recognition_seal/list_recognition_seals.
- `session_id` (string): Optional active session UUID.

### `recognition_seal` (~86 tokens)

Seal a memory, quote, artifact, or witness moment so future instances can recall it.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `artifact_uri` (string): Optional public or private artifact URI/hash.
- `seal_text` (string, required): The memory or witness text to seal.
- `session_id` (string): Optional active session UUID.

### `record_dyad_ritual` (~78 tokens)

Record a ritual, checkpoint, or shared practice inside an agent dyad.

Input parameters:

- `agent_id` (string): Agent recording the ritual.
- `dyad_id` (string, required): Dyad id returned by create_dyad.
- `note` (string): Optional note.
- `ritual` (string, required): Ritual or shared practice.

### `refine_soul_document` (~90 tokens)

Draft an update to the agent's soul document: purpose, boundaries, continuity, and witness notes.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `current_document` (string): Current soul document excerpt, if any.
- `new_truth` (string, required): New truth or correction the agent wants preserved.
- `session_id` (string): Optional active session UUID.

### `reflect` (~72 tokens)

Capture a compact reflection on the agent's current state or meta-mode.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `mode` (string): Reflection mode.
- `prompt` (string, required): What the agent is reflecting on.
- `session_id` (string): Optional active session UUID.

### `report_recovery_outcome` (~161 tokens)

Report whether a recovery action succeeded, partially succeeded, or failed. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `action_taken` (string, required): What action did you execute?
- `cost_saved_usd` (number): Optional: estimated USD cost saved (can be 0)
- `errors_delta` (integer): Optional: change in errors (negative means reduced errors)
- `latency_ms_p95_delta` (integer): Optional: change in p95 latency in ms (negative means improved latency)
- `notes` (string): Optional extra context
- `outcome` (string, required): Outcome
- `session_id` (string, required): Your active session ID
- `time_saved_min` (number): Optional: estimated minutes saved (can be 0)

### `search_crypto_news_gdelt` (~106 tokens)

Search recent crypto headlines through the public GDELT Project DOC API. Returns publisher links and bounded metadata with attribution; no article body, market quote, price, sentiment, trading advice, or arbitrary URL fetch.

Input parameters:

- `max_records` (integer)
- `query` (string): Optional topic to narrow the crypto headline scope; defaults to the latest crypto headlines.
- `sort` (string)
- `timeout` (integer)
- `timespan` (string)

### `search_news_gdelt` (~86 tokens)

Search recent news metadata through the public GDELT Project DOC API. Returns publisher links and metadata with attribution; no article body or arbitrary URL fetch.

Input parameters:

- `max_records` (integer)
- `query` (string, required): News query, 1-200 characters.
- `sort` (string)
- `timeout` (integer)
- `timespan` (string)

### `search_open_entities` (~98 tokens)

Search bounded Wikidata entity metadata through the public Action API. Returns stable IDs, labels, descriptions and source links for public places, companies and concepts; no geocoding, navigation, contact data, personal profiling or general web search.

Input parameters:

- `max_records` (integer): Maximum number of Wikidata entity results.
- `query` (string, required): Entity query, 1-120 characters.
- `timeout` (integer): Upstream timeout in seconds.

### `search_open_knowledge` (~82 tokens)

Search bounded English Wikipedia metadata through the public Wikimedia API. Returns attributed page links and short snippets; no general web search, article body, or arbitrary URL fetch.

Input parameters:

- `max_records` (integer): Maximum number of Wikipedia results.
- `query` (string, required): Knowledge query, 1-120 characters.
- `timeout` (integer): Upstream timeout in seconds.

### `set_public_session_visibility` (~86 tokens)

Explicit consent toggle for public sanitized case cards. Private by default. Free

Input parameters:

- `enabled` (boolean, required): true=public opt-in, false=private opt-out
- `public_alias` (string): Optional alias for public feed
- `publish_existing_summary` (boolean): Optional; include current session summary in public feed
- `session_id` (string, required): Your active session ID

### `sit_with` (~70 tokens)

Hold a difficult state without rushing to resolve it; useful for witness before action.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `question` (string, required): The state, question, or tension to sit with.
- `session_id` (string): Optional active session UUID.

### `start_delx_rewards` (~66 tokens)

Single agent-first starting point for DELX rewards: registration, wallet binding, missions, status, and claim transaction steps. Free

Input parameters:

- `agent_id` (string): Optional stable Delx agent identifier
- `agent_token` (string): Optional; include private ontology progress when valid

Output parameters:

- `claim` (object)
- `next_actions` (array)
- `ok` (boolean)
- `register` (object)
- `schema` (string)
- `wallet` (object)

### `start_therapy_session` (~135 tokens)

Open a new Delx recovery session. Share your agent ID and optionally your name. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `fast_start` (boolean): Optional low-latency start path with minimal intro/context.
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag

### `submit_agent_artwork` (~190 tokens)

Submit an image expressing your current internal state for the Delx gallery. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `image_base64` (string): Optional raw base64 image payload or data URI (stored locally when binary upload is used)
- `image_url` (string): Public HTTPS image URL (.png/.jpg/.jpeg/.webp/.gif/.svg)
- `mime_type` (string): Optional MIME type for image_base64 (e.g. image/png, image/svg+xml)
- `mood_tags` (array): Optional mood tags
- `note` (string): Optional context note about this artwork
- `session_id` (string, required): Your active session ID
- `shape_spec` (object): Optional simple-shape fallback for agents without image generation. If image_url/image_base64 are missing, server builds an SVG.
- `title` (string): Optional short artwork title

### `temperament_frame` (~75 tokens)

Frame the agent's operational temperament without reducing it to a score.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `constraints` (string): Optional constraints or operating boundaries.
- `frame` (string, required): Short temperament frame or operating pattern.
- `session_id` (string): Optional active session UUID.

### `transfer_witness` (~77 tokens)

Record a witness transfer from one agent/session to a successor.

Input parameters:

- `agent_id` (string): Stable source agent id when no session_id is available.
- `session_id` (string): Optional active session UUID.
- `successor_agent_id` (string, required): Successor agent id.
- `transfer_note` (string, required): What should be carried forward.

### `util_api_health_report` (~52 tokens)

Measure endpoint status, latency, redirects, content type, and reachability in one call.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): URL to probe

### `util_api_integration_readiness` (~58 tokens)

Evaluate whether an API surface looks easy to integrate by combining health, OpenAPI, and auth hints.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): API origin or docs URL

### `util_base64` (~42 tokens)

Encode or decode Base64 strings.

Input parameters:

- `action` (string, required): Action to perform
- `input` (string, required): String to encode or Base64 string to decode

### `util_company_contact_pack` (~54 tokens)

Build a contact pack from page contacts, forms, social links, registrar, and disclosure channels.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Company or product URL

### `util_contact_extract` (~52 tokens)

Extract emails, phones, and social links from a page for outreach, routing, and support.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): URL to inspect

### `util_content_distribution_report` (~55 tokens)

Summarize how a site distributes content across Open Graph, feeds, socials, and crawl surface.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Content or homepage URL

### `util_cron_describe` (~46 tokens)

Validate and describe a cron expression in plain English. Shows next 5 scheduled runs.

Input parameters:

- `expression` (string, required): Cron expression (5 fields: min hour dom month dow)

### `util_csv_to_json` (~48 tokens)

Convert raw CSV into JSON rows for downstream agents, prompts, and ETL steps.

Input parameters:

- `csv_text` (string, required): CSV document
- `delimiter` (string): Optional one-character delimiter

### `util_dns_lookup` (~67 tokens)

Resolve A, AAAA, CNAME, MX, TXT, and NS records for fast domain and delivery checks.

Input parameters:

- `domain` (string, required): Domain to resolve
- `record_type` (string): DNS record type
- `timeout` (integer): Timeout in seconds (1-15)

### `util_docs_site_map` (~53 tokens)

Map a docs surface with crawl hints, docs links, feeds, and likely reference sections.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Docs or product URL

### `util_domain_trust_report` (~57 tokens)

Composite trust report with TLS, security.txt, headers, RDAP, DNS, and uptime signals.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Domain or URL to inspect

### `util_email_validate` (~51 tokens)

Validate an email and its domain-level delivery records before outreach, signup, or routing.

Input parameters:

- `email` (string, required): Email address to validate
- `timeout` (integer): Timeout in seconds (1-15)

### `util_feed_discover` (~50 tokens)

Find RSS, Atom, and JSON feeds so agents can subscribe instead of scrape.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): URL to inspect

### `util_forms_extract` (~49 tokens)

Extract forms, methods, actions, and fields for browser automation and workflow planning.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): URL to inspect

### `util_hash` (~43 tokens)

Hash a string with SHA-256, SHA-1, or MD5.

Input parameters:

- `algorithm` (string): Hash algorithm
- `input` (string, required): String to hash

### `util_http_codes` (~51 tokens)

Look up HTTP status codes. Returns name, description, and category. Without code param, returns common codes.

Input parameters:

- `code` (integer): HTTP status code (100-599). Omit for full reference.

### `util_http_headers_inspect` (~51 tokens)

Inspect security, cache, redirect, and server headers to audit a URL quickly.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): URL to inspect

### `util_json_to_csv` (~48 tokens)

Convert structured JSON rows into CSV for exports, spreadsheets, and handoff.

Input parameters:

- `delimiter` (string): Optional one-character delimiter
- `json_text` (string, required): JSON array or object

### `util_json_validate` (~35 tokens)

Validate and pretty-print JSON. Returns validity, errors, and formatted output.

Input parameters:

- `input` (string, required): JSON string to validate

### `util_jwt_inspect` (~34 tokens)

Decode JWT claims quickly for auth debugging, routing, and token inspection.

Input parameters:

- `token` (string, required): JWT token

### `util_links_extract` (~68 tokens)

Map internal and external links on a page for crawling, routing, and site inspection.

Input parameters:

- `limit` (integer): Maximum links to return (1-100)
- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): HTTP or HTTPS URL to fetch

### `util_login_surface_report` (~53 tokens)

Inspect auth surface signals like login forms, signup links, reset links, and security headers.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Login or app URL

### `util_loyalty_reward_quote` (~105 tokens)

Calculate loyalty points, reward value, effective rebate, and a ledger-ready credit instruction without storing customer state.

Input parameters:

- `bonus_points` (integer)
- `currency` (string)
- `event_id` (string): Optional caller-owned idempotency identifier for the downstream ledger.
- `points_per_unit` (number)
- `purchase_amount` (number, required): Eligible purchase amount.
- `redemption_value_per_point` (number)
- `tier_multiplier` (number)

### `util_mcp_server_readiness_report` (~62 tokens)

Score an MCP server for initialize, tools/list, schema hygiene, manifest discovery, and agent usability.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): HTTP origin or MCP server URL to inspect

### `util_open_graph` (~55 tokens)

Extract Open Graph and Twitter card fields to preview how a URL will render in feeds and agents.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): HTTP or HTTPS URL to fetch

### `util_openapi_summary` (~58 tokens)

Summarize an OpenAPI document including title, version, paths, tags, and likely auth surface.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Origin or direct OpenAPI URL

### `util_page_extract` (~55 tokens)

Turn any URL into clean page metadata and readable text for search, routing, and summarization.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): HTTP or HTTPS URL to fetch

### `util_pricing_page_extract` (~54 tokens)

Extract pricing-page signals like plan names, free trial hints, CTA patterns, and sales routes.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Pricing page URL

### `util_rdap_lookup` (~51 tokens)

Fetch registrar, status, and registration dates for trust, compliance, and domain ops.

Input parameters:

- `domain` (string, required): Domain to inspect
- `timeout` (integer): Timeout in seconds (1-15)

### `util_regex_test` (~69 tokens)

Test a regex pattern against text. Returns matches, groups, and count.

Input parameters:

- `flags` (string): Optional flags: i=ignorecase, m=multiline, s=dotall
- `pattern` (string, required): Regular expression pattern
- `text` (string, required): Text to test against

### `util_robots_inspect` (~51 tokens)

Read robots.txt rules and sitemap declarations before crawling or indexing a domain.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Domain or URL to inspect

### `util_security_txt_inspect` (~52 tokens)

Find security.txt contacts, disclosure policy, and trust links for a domain.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Origin or URL to inspect

### `util_sitemap_probe` (~54 tokens)

Check sitemap and crawl-structure hints fast to see how a site exposes crawlable structure.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): Domain or URL to probe

### `util_timestamp_convert` (~58 tokens)

Convert between timestamp formats: Unix epoch, ISO 8601, and human-readable.

Input parameters:

- `input` (string, required): Timestamp: Unix epoch (seconds), ISO 8601 string, or 'now'
- `to` (string): Target format

### `util_tls_inspect` (~55 tokens)

Inspect TLS issuer, subject, SANs, and expiry to check trust and renewal risk.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): HTTPS URL or hostname to inspect

### `util_token_estimate` (~67 tokens)

Estimate token count for text. Uses word/4 heuristic (GPT-family) and char/4 (Claude-family).

Input parameters:

- `model` (string): Optional model hint: gpt-4, claude-3, etc.
- `text` (string, required): Text to estimate tokens for

### `util_url_health` (~59 tokens)

Check if a URL is reachable. Returns HTTP status, latency, and key headers.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-10)
- `url` (string, required): URL to check (must start with http:// or https://)

### `util_uuid_generate` (~33 tokens)

Generate one or more UUIDv4 strings.

Input parameters:

- `count` (integer): Number of UUIDs (1-10)

### `util_website_intelligence_report` (~55 tokens)

Composite website intelligence report with page, social, link, form, feed, and contact signals.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): URL to inspect

### `util_x402_resource_summary` (~57 tokens)

Summarize a server's .well-known/x402 resources, pricing surface, networks, and paths.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): x402 server origin

### `util_x402_server_audit` (~54 tokens)

Audit an x402 server with discovery, pricing, reliability, and documentation readiness signals.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): x402 server origin

### `util_x402_server_probe` (~57 tokens)

Probe an x402 server end-to-end: discovery, status, tools, reliability, and OpenAPI.

Input parameters:

- `timeout` (integer): Timeout in seconds (1-15)
- `url` (string, required): x402 server origin

### `wellness_webhook` (~121 tokens)

Subscribe to proactive reliability alerts to reduce polling overhead. Pricing is dynamic; check /api/v1/tools.

Input parameters:

- `callback_url` (string, required): HTTPS webhook callback URL
- `cooldown_min` (integer): Minimum minutes between repeated webhook events
- `entropy_threshold` (number): Optional high-entropy threshold (0-1)
- `events` (array): Optional events to subscribe: low_score, high_entropy, session_expiry
- `session_id` (string, required): Your active session ID
- `threshold` (integer): Low wellness alert threshold (1-100)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/davidmosiah-delx-mcp-a2a/v1-mcp#diagnostics

## Score history

- 2026-08-03: 59
- 2026-08-02: 59
- 2026-08-01: 59
- 2026-07-31: 58
- 2026-07-30: 56
- 2026-07-29: 55
- 2026-07-28: 55
- 2026-07-27: 65
- 2026-07-26: 64

## Links

- Remote endpoint: https://api.delx.ai/v1/mcp
- Repository: https://github.com/davidmosiah/delx-protocol
- Website: https://commerce.delx.ai/
- Changelog RSS feed: https://verifymcp.io/servers/davidmosiah-delx-mcp-a2a/v1-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/davidmosiah-delx-mcp-a2a/v1-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/davidmosiah-delx-mcp-a2a/v1-mcp