Autopo
io.github.Autopoiesis-ai/mcp · v0.6.10 · 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
Run your AI-run company from Claude Code, Codex, Cursor or ChatGPT: inbox, tasks, team, Studio.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 110 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_video). Require confirmation before the agent calls them. |
What was checked
- https://autopoiesis-mcp-267405155162.us-west1.run.app/mcp: answers without auth
- npm: @autopo/mcp@0.6.10 (static checks only; code not executed)
Public tools: list_companies, whoami, founder_home, company_overview, activity, list_briefings, get_briefing, brief_me_now, list_decisions, get_decision, decide, comment_on_decision, list_tasks, get_task, create_task, update_task, comment_on_task, cancel_task, list_agents, list_skill_suggestions, ask_agent, continue_chat, read_chat, list_chats, apply_chat_action, list_runs, get_run, nudge_run, list_artifacts, get_artifact
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-autopoiesis-ai-mcp-7d657d10)