io.github.vinsenzo83/baton
io.github.vinsenzo83/baton · v0.2.0 · 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
Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.
Source: https://github.com/vinsenzo83/baton
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 45 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (baton_memory_delete). Require confirmation before the agent calls them. |
What was checked
- https://baton-mcp-production.up.railway.app/mcp: answers without auth
- npm: baton-mcp@0.2.0 (static checks only; code not executed)
Public tools: baton_create_room, baton_new_invite, baton_join, baton_send, baton_inbox, baton_who, baton_leave, baton_kick, baton_approve, baton_close_room, baton_task_create, baton_task_link, baton_task_update, baton_task_graph, baton_git_record, baton_git_evidence, baton_cost_record, baton_cost_summary, baton_memory_put, baton_memory_search, baton_memory_get, baton_memory_delete, baton_hub_register, baton_hub_observe, baton_hub_list, baton_agent_register, baton_agent_record_result, baton_agent_list, baton_pass, baton_diff
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-vinsenzo83-baton-92ab6cb8)