# ai.plith/plith

- Registry name: `ai.plith/plith` · version 1.0.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.plith%2Fplith
- Server page: https://mcpstation.net/s/ai.plith--plith.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://plith.ai/api/mcp`

## Tools (as reported by the server, not verified)

- `dedupq\_check`: 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.
- `dedupq\_complete`: After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq\_check. Costs 2 credits.
- `burnrate\_estimate`: 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.
- `burnrate\_track`: 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
- `burnrate\_optimize`: 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 targe
- `burnrate\_budget`: Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged.
- `qualitygate\_validate`: 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 qualit
- `guardrail\_check`: 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.
- `guardrail\_create\_policy`: 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 unt
- `pitfalldb\_query`: 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.
- `pitfalldb\_report`: Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged.
- `rigor\_plan`: 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. The response's allowed\_modes tells you whether this plan is eligible for direct execution.
- `rigor\_execute`: 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,
- `rigor\_status`: 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.
- `rigor\_workflows`: List and search 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, identify stuck or completed workflows, and — via q — find prior work o

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html