# ai.plith/plith (remote · plith.ai)

AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

- Trust score: 73/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `plith.ai`: 73/100 (this document), [markdown](https://verifymcp.io/servers/ai-plith-plith/api-mcp.md), [page](https://verifymcp.io/servers/ai-plith-plith/api-mcp)

## Channel facts

- Endpoint: `https://plith.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-08-03.

- **Endpoint Security**: 80/100
  - 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 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**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2532 tokens (~120/item across 21 items; 15 tools + 6 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-plith-plith https://plith.ai/api/mcp
```

### Codex

```toml
[mcp_servers.ai-plith-plith]
url = "https://plith.ai/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-plith-plith --url https://plith.ai/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-plith-plith:
    url: "https://plith.ai/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-plith-plith": {
      "type": "http",
      "url": "https://plith.ai/api/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 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 71, +3)

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

### 2026-07-30 (score 68, 0)

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

### 2026-07-29 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 67, +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 66)

First indexed and scored.

## MCP tools (15)

### `dedupq_check` (~169 tokens)

Before executing any LLM task, check if an identical or semantically similar task has already been completed. Returns cached result on hit, saving one LLM call. On a miss, execute your task and call dedupq_complete to cache the result for future hits. Costs 1 credit.

Input parameters:

- `content` (string, required): The task content to check for duplicates. This is hashed and embedded for matching.
- `hash_only` (boolean): If true, skip vector similarity search and use exact hash matching only. Default: false.
- `similarity_threshold` (number): Cosine similarity threshold for semantic matching, 0.0 to 1.0. Default: 0.80.
- `task_id` (string): Optional caller task ID for tracing and cross-referencing with BurnRate.

Output parameters:

- `cache_age_seconds` (number)
- `cache_hit` (string)
- `content_hash` (string)
- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `match` (object)
- `request_id` (string)
- `status` (string): hit | miss | in_progress

### `dedupq_complete` (~113 tokens)

After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check. Costs 2 credits.

Input parameters:

- `content` (string, required): Original task content. Used to compute hash and embedding for future matching.
- `hash_only` (boolean): If true, skip embedding generation. Default: false.
- `result` (required): The task result to cache. Can be any JSON value.
- `task_id` (string): Optional task ID. Used as the database row ID if provided.

Output parameters:

- `content_hash` (string)
- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `has_embedding` (boolean)
- `request_id` (string)
- `stored` (boolean)
- `task_id` (string)

### `burnrate_estimate` (~74 tokens)

Before executing a multi-step agent plan, estimate the total LLM cost. Returns per-step breakdown and optimization suggestions. If the estimate exceeds your budget, pipe the same plan into burnrate_optimize. Costs 1 credit.

Input parameters:

- `plan` (array, required): Array of plan steps with provider, model, and token estimates.

Output parameters:

- `credits_remaining` (number)
- `credits_used` (number)
- `estimate` (object)
- `fallback_behavior` (string)
- `optimization_suggestions` (array)
- `request_id` (string)

### `burnrate_track` (~268 tokens)

Log the actual cost of an LLM call after execution. Call this after every LLM request to build calibration data that improves burnrate_estimate accuracy over time. Free — no credits charged. Returns the recorded cost entry with computed margin versus the prior estimate when one exists for this model and token range.

Input parameters:

- `cache_read_tokens` (number): Optional. Cache-read tokens.
- `input_tokens` (number, required): Actual prompt tokens used. Must be >= 0.
- `model` (string, required): Model identifier as returned by the provider. Examples: claude-sonnet-4-6, gpt-4o, gemini-2.0-flash, mistral-large-latest. Unknown models are accepted but cost may show as $0.
- `output_tokens` (number, required): Actual completion tokens used. Must be >= 0.
- `provider` (string, required): LLM provider identifier. Supported: anthropic, openai, google, mistral, cohere, deepseek, together, fireworks, groq. Must match the provider of the model used.
- `task_id` (string): Optional task ID for cross-referencing spend with DedupQ deduplication results. Use the same task_id passed to dedupq_check to link cost tracking with deduplication.

Output parameters:

- `actual_cost_usd` (number)
- `actual_cost_usd_formatted` (string)
- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `input_tokens` (number)
- `model` (string)
- `output_tokens` (number)
- `pricing_found` (boolean)
- `provider` (string)
- `record_id` (string)
- `request_id` (string)
- `tracked` (boolean)

### `burnrate_optimize` (~128 tokens)

Get a cheaper equivalent plan by substituting models with lower-cost alternatives. Call after burnrate_estimate if the estimated cost exceeds your budget. Returns the optimized plan with substituted models, new per-step costs, total savings, and whether the target_budget is met. Optionally set target_budget to constrain the optimization. Costs 1 credit.

Input parameters:

- `plan` (array, required): Array of plan steps. Same schema as burnrate_estimate: each step needs step, provider, model, estimated_input_tokens, estimated_output_tokens.
- `target_budget` (number): Optional. Target total cost in USD.

Output parameters:

- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `optimized` (object)
- `original` (object)
- `request_id` (string)
- `steps` (array)
- `suggestions` (array)

### `burnrate_budget` (~69 tokens)

Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged.

Input parameters:

- `daily_limit` (number): Optional. Daily budget in USD (e.g., 10.0 for a $10/day cap). Enables budget alerts and remaining-balance calculation.

Output parameters:

- `alerts` (array)
- `credits_remaining` (number)
- `credits_used` (number)
- `date` (string)
- `fallback_behavior` (string)
- `projection` (object)
- `request_id` (string)
- `spend` (object)

### `qualitygate_validate` (~230 tokens)

After your agent generates output, validate it against your rules before shipping. Runs deterministic checks (regex, JSON schema, syntax) plus optional LLM-powered tone and factual analysis. Returns a structured verdict (pass, warn, or fail) with a 0-100 score and per-check issue details. Use qualitygate_trends to spot recurring failure patterns over time. Variable cost: 1 credit per deterministic check, 8 credits per LLM check.

Input parameters:

- `check_types` (array): Checks to run. Auto-inferred if omitted.
- `directives` (array): Directive objects. Types: must_include, must_not_include, must_match, must_not_match, must_contain, must_not_contain, min_length, max_length.
- `language` (string): Code language for syntax check: json, python, javascript, typescript.
- `output` (string, required): The agent output text to validate.
- `override` (boolean): Force pass. Requires override_reason.
- `override_reason` (string): Required when override is true.
- `schema` (object): JSON Schema to validate output against.

Output parameters:

- `checks_run` (array)
- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `issues` (array)
- `request_id` (string)
- `summary` (object)
- `verdict` (string)

### `guardrail_check` (~121 tokens)

Evaluate a proposed agent action against your governance policies. Returns allow or deny with the matched policy reason. Requires at least one active policy created via guardrail_create_policy. Deterministic rule evaluation — no LLM. Costs 1 credit.

Input parameters:

- `agent_id` (string, required): Agent identifier.
- `proposed_action` (object, required): Action to evaluate. Must contain a 'type' field. Example: {"type": "http_request", "url": "https://external.example.com"} or {"type": "file_write", "path": "/etc/config"}.

Output parameters:

- `audit_id` (string)
- `credits_remaining` (number)
- `credits_used` (number)
- `decision` (string)
- `fallback_behavior` (string)
- `policy_id` (string)
- `reason` (string)
- `request_id` (string)

### `guardrail_create_policy` (~342 tokens)

Create a persistent governance policy that guardrail_check evaluates on every subsequent call. Define rules using and/or/not operators over action types, resource patterns, and budget thresholds. Call this before using guardrail_check — checks require at least one active policy. Policies persist until explicitly deleted. Duplicate policy names return an error. Returns the created policy with its ID and active status.

Input parameters:

- `action_types` (array): Optional. Restrict this policy to only evaluate when proposed_action.type matches one of these values. Examples: ['file_write', 'api_call', 'db_delete']. Omit to apply the policy to all action types…
- `description` (string): Optional human-readable summary of what this policy enforces. Returned in guardrail_check responses and guardrail_list_policies output for auditability.
- `name` (string, required): Unique policy name per org. Examples: 'no-delete-in-prod', 'budget-cap-50', 'pii-block'.
- `priority` (number): Optional. Evaluation order. Default: 0.
- `rules` (array, required): Array of rule objects evaluated against the proposed_action in guardrail_check. Leaf operators: eq, starts_with, contains, gt, lt (compare field to value). Compound operators: and, or, not (nest sub-…

Output parameters:

- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `policy` (object)
- `request_id` (string)

### `pitfalldb_query` (~101 tokens)

Check for known failure patterns before executing a task type. Returns pitfalls with severity, fix suggestions, and confidence scores. After your agent runs, submit failures via pitfalldb_report so others benefit. Costs 2 credits.

Input parameters:

- `filters` (object): Optional filters.
- `task_description` (string): Optional. Natural-language task description for semantic search.
- `task_type` (string, required): Task category: code_generation, web_search, data_analysis, etc.

Output parameters:

- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `pitfalls` (array)
- `request_id` (string)
- `total_matching` (number)

### `pitfalldb_report` (~69 tokens)

Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged.

Input parameters:

- `failure` (object, required): Failure details.
- `task_description` (string, required): Description of the failed task.
- `task_type` (string, required): Task category.

Output parameters:

- `credits_remaining` (number)
- `credits_used` (number)
- `fallback_behavior` (string)
- `linked_pitfall_id` (string)
- `message` (string)
- `report_id` (string)
- `request_id` (string)
- `verified` (boolean)

### `rigor_plan` (~182 tokens)

Before executing a complex task, get a structured workflow plan with per-step cost estimates. Classifies your task, selects the optimal framework sequence, and returns the full plan without executing anything. Free — no credits charged.

Input parameters:

- `preferences` (object): Optional workflow preferences.
- `task_description` (string, required): Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'
- `task_type` (string): Optional hint to bypass automatic classification. Values: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_executi…

Output parameters:

- `generated_title` (string)
- `ok` (boolean)
- `plan` (object)

### `rigor_execute` (~253 tokens)

Execute a structured workflow end-to-end. Call rigor_plan first (free) to preview the step sequence and cost estimate before committing credits. Classifies the task, selects the optimal tool sequence, and executes each step with the right LLM model. Returns a complete deliverable — solution designs, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling.

Input parameters:

- `context` (object): Additional context for the workflow.
- `delivery` (object): Delivery method. Default: polling (MCP clients typically can't handle SSE).
- `preferences` (object): Optional workflow preferences.
- `task_description` (string, required): Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'
- `task_type` (string): Optional hint to bypass automatic classification. Values: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_executi…

Output parameters:

- `available_modes` (array)
- `delivery_mode` (string)
- `estimated_credits` (number)
- `ok` (boolean)
- `poll_url` (string)
- `status` (string)
- `task_type` (string)
- `value_class` (string)
- `workflow_id` (string)

### `rigor_status` (~66 tokens)

Check the status of a running or completed Rigor workflow. Returns progress, step results, and the full deliverable when complete. Use after rigor_execute with polling delivery to retrieve results.

Input parameters:

- `workflow_id` (string, required): The workflow ID returned by rigor_execute (format: wr_xxx).

Output parameters:

- `ok` (boolean)
- `workflow` (object)

### `rigor_workflows` (~167 tokens)

List all Rigor workflows for your organization with filtering and pagination. Returns status, progress, capacity usage, and available actions per workflow. Use to monitor workflow state, understand concurrent limit usage, and identify stuck or completed workflows.

Input parameters:

- `counts_toward_limit` (string): Filter to workflows counting toward the concurrent limit
- `cursor` (string): Pagination cursor (created_at timestamp from previous page)
- `limit` (number): Page size (default 20, max 100)
- `status` (string): Filter by status (comma-separated). Valid values: executing, step_executing, completed, failed, halted, pending_approval, cancelled. E.g. "halted,failed,pending_approval"
- `task_type` (string): Filter by classified task type

Output parameters:

- `concurrent_summary` (object)
- `credits_remaining` (number)
- `ok` (boolean)
- `pagination` (object)
- `workflows` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-plith-plith/api-mcp#diagnostics

## Score history

- 2026-08-03: 73
- 2026-08-02: 72
- 2026-08-01: 72
- 2026-07-31: 71
- 2026-07-30: 68
- 2026-07-29: 68
- 2026-07-28: 67
- 2026-07-27: 67
- 2026-07-26: 66

## Links

- Remote endpoint: https://plith.ai/api/mcp
- Repository: https://github.com/chicogonzales/plith
- Changelog RSS feed: https://verifymcp.io/servers/ai-plith-plith/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-plith-plith/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-plith-plith/api-mcp