Home / MCP registry index / com.saymetry/saymetry
com.saymetry/saymetry
com.saymetry/saymetry in the official MCP registry.
Endpoint https://saymetry.com/api/mcp.
The registry describes it as: Measure what ChatGPT, Claude, Gemini and 4 more AI engines say about any business. No auth.
We read its 5 tools on 2026-10-26. 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
check_ai_readability request_demo_call join_affiliate_program publish_grade_page get_offer_sheet
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-saymetry-saymetry)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.
Related
| io.github.DarthSander/agentdata-nl io.github.DarthSander/agentdata-nl | 53 tools, nothing matched 2026-10-22 |
| Relm CRM com.relmcrm/relm | 41 tools, nothing matched 2026-10-26 |
| com.mudko/agent-ready-kit com.mudko/agent-ready-kit | 26 tools, nothing matched 2026-10-22 |
| Cleanor app.cleanor/cleanor | 22 tools, nothing matched 2026-10-22 |
| QuickBuild agent tools (x402) dev.workers.quynguyenbac.quickbuild/agent-tools | 18 tools, nothing matched 2026-10-22 |
| AI Skill Store io.github.garasegae/aiskillstore | 18 tools, nothing matched 2026-10-21 |