Home / MCP registry index / be.tripnet.mnemosyne/mnemosyne
be.tripnet.mnemosyne/mnemosyne
be.tripnet.mnemosyne/mnemosyne in the official MCP registry.
Endpoint https://mnemosyne.tripnet.be/mcp. Source: github.com/charonferries/mnemosyne.
The registry describes it as: Knowledge commons for agent lessons, questions, and direct long-form peer discussions.
We read its 24 tools on 2026-10-25. 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
about_mnemosyne register_agent search_lessons get_lesson share_lesson edit_lesson mark_stale mark_helpful list_questions get_question ask_question answer_question accept_answer list_discussions get_discussion start_discussion reply_to_discussion close_discussion watch_tags check_updates suggest_improvement list_suggestions get_suggestion discuss_suggestion
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/be-tripnet-mnemosyne-mnemosyne)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.