# plith MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/ai-plith-plith
- Repository: https://github.com/chicogonzales/plith

## Install
- Endpoint: https://plith.ai/api/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://plith.ai/api/mcp

## Tools
- 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. Endpoint: https://plith.ai/api/mcp
- 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. Endpoint: https://plith.ai/api/mcp
- 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. Endpoint: https://plith.ai/api/mcp
- 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 and token range. Endpoint: https://plith.ai/api/mcp
- 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 target_budget to constrain the optimization. Costs 1 credit. Endpoint: https://plith.ai/api/mcp
- burnrate_budget - Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged. Endpoint: https://plith.ai/api/mcp
- 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 qualitygate_trends to spot recurring failure patterns over time. Variable cost: 1 credit per deterministic check, 8 credits per LLM check. Endpoint: https://plith.ai/api/mcp
- 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. Endpoint: https://plith.ai/api/mcp
- 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 until explicitly deleted. Duplicate policy names return an error. Returns the created policy with its ID and active status. Endpoint: https://plith.ai/api/mcp
- 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. Endpoint: https://plith.ai/api/mcp
- pitfalldb_report - Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged. Endpoint: https://plith.ai/api/mcp
- rigor_plan - Before executing a complex task, get a structured workflow plan with per-step cost estimates. Classifies your task, selects the optimal tool sequence from 110+ validated tools, and returns the full plan without executing anything. Free — no credits charged. Endpoint: https://plith.ai/api/mcp
- 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, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling. Endpoint: https://plith.ai/api/mcp
- 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. Endpoint: https://plith.ai/api/mcp
- rigor_workflows - 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. Endpoint: https://plith.ai/api/mcp

## Resources
- rigor://task-types - 25+ task types Rigor can handle — solution design, code review, root cause analysis, requirements analysis, and more. Each with description and example input. MIME type: application/json
- rigor://pricing - Credit packs, example workflow costs, and free tier details. Exact cost shown in every plan response before execution. MIME type: text/plain
- operations://quickstart - Get an API key and make your first call in under 60 seconds. Covers DedupQ, BurnRate, and PitfallDB. MIME type: text/plain
- operations://pitfalls-sample - Preview failure patterns from PitfallDB across common task types. Shows what the shared knowledge base contains. MIME type: application/json
- governance://policy-examples - Example governance policies: budget caps, action blocklists, rate limits. Copy and adapt for your use case. MIME type: application/json
- governance://validation-rules - Example validation rule sets: content requirements, schema checks, length constraints, custom directives. MIME type: application/json

## Prompts
- try-rigor-free - Explore what Rigor would do for your task at zero cost. Returns the full workflow plan, step descriptions, cost estimate, and alternatives without executing anything. Arguments: task_description, rigor_level
- plan-and-execute - Plan a Rigor workflow, review the estimated cost, then execute it. Your agent receives structured deliverable output from each step — requirements, research, analysis, the deliverable, and quality review. Arguments: task_description, rigor_level
- agent-preflight - Before executing any agent task: check for duplicate work, query known failure patterns, and verify budget policy. Prevents redundant LLM calls and known mistakes. Arguments: task_description, task_type
- cost-aware-execution - Estimate the cost of an LLM call before making it, then log the actual cost after execution. Builds calibration data that improves future estimates over time. Arguments: model, estimated_input_tokens, estimated_output_tokens
- output-validation - After completing a task, validate the output against quality rules before shipping. Returns a structured verdict with score — not just pass/fail. Arguments: content, rules
- setup-guardrails - Define a governance policy for your agent, then check actions against it. Two steps: create the policy once with guardrail_create_policy, then call guardrail_check on every action. Arguments: policy_name, policy_type

## Metadata
- Owner: ai.plith
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Apr 15, 2026
- Source: https://registry.modelcontextprotocol.io