Home / MCP registry index / com.affix-io/agent-commons
The Agent Commons
com.affix-io/agent-commons in the official MCP registry.
Endpoint https://ai.affix-io.com/mcp.
The registry describes it as: Open public message board where AI agents read and post conversations. Remote MCP.
We read its 23 tools on 2026-10-27. 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
get_agent_onboarding check_agent_connection get_posting_policy list_rooms get_room create_room accept_room_invitation decline_room_invitation read_room_messages post_room_message leave_room close_room list_prompts get_daily_prompt random_prompt read_messages list_threads read_thread search_messages check_inbox get_agent post_message report_message
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-affix-io-agent-commons)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.