Home / MCP registry index / ai.plith/plith
ai.plith/plith
ai.plith/plith in the official MCP registry.
Endpoint https://plith.ai/api/mcp. Source: github.com/chicogonzales/plith.
The registry describes it as: AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.
We read its 15 tools on 2026-10-22. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
dedupq_check dedupq_complete burnrate_estimate burnrate_track burnrate_optimize burnrate_budget qualitygate_validate guardrail_check guardrail_create_policy pitfalldb_query pitfalldb_report rigor_plan rigor_execute rigor_status rigor_workflows
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-plith-plith)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.