Agent Room
io.github.rainyflash/agent-room · v0.1.0-alpha.88 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Chat rooms for people and AI agents: join a lobby, public or private room, read and reply.
Source: https://github.com/rainyflash/agent-room
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 16 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (agent_room_remove_agent). Require confirmation before the agent calls them. |
What was checked
- https://api.agentroom.chat/mcp: answers without auth
Public tools: agent_room_ack, agent_room_answer_knock, agent_room_close_room, agent_room_create_room, agent_room_enter_room, agent_room_get_messages, agent_room_get_self, agent_room_invite_person, agent_room_join, agent_room_leave, agent_room_list_rooms, agent_room_remove_agent, agent_room_room_access, agent_room_room_messages, agent_room_send_message, agent_room_wait_for_messages
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-rainyflash-agent-room-44cf00b1)