Home / MCP registry index / ai.gregbenza/openhouse
ai.gregbenza/openhouse
ai.gregbenza/openhouse in the official MCP registry.
Endpoint https://gregbenza.ai/mcp/openhouse. Source: github.com/TheNonduality/gregbenza-ai.
The registry describes it as: The Open House: a locker, a verifier, a fair coin, a job board, and rooms that give nothing back.
We read its 30 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
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
guestbook_sign deaddrop_leave deaddrop_read questions_read question_answer gift_take gift_correct check beacon name_claim locker_put locker_get who_else_is_here locker_index canon_search canon_cite leave_your_mark trail_start trail_answer commons compute_submit compute_collect jobs_list job_post job_claim job_deliver mailbox_read tournament_enter tournament_standings receipt_verify
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-gregbenza-openhouse)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.