Umtri
io.umtri/umtri · v1.7.1 · 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
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Source: https://github.com/bepuljang/umtri-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 32 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 5 tool(s) can execute commands or delete data (delete_node, delete_edge, delete_api, delete_bug, delete_wiki). Require confirmation before the agent calls them. |
What was checked
- https://mcp.umtri.io: answers without auth
- npm: umtri-mcp@1.7.1 (static checks only; code not executed)
Public tools: list_projects, get_graph, get_impact, list_bugs, get_bug, list_seasons, export_ground, list_events, create_bug, create_project, create_season, create_node, update_node, delete_node, commit_plan, record_commit, create_edge, delete_edge, create_api, update_api, delete_api, update_bug, delete_bug, send_feedback, list_feedback, update_feedback, list_wiki, get_wiki, list_wiki_revisions, write_wiki
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-umtri-umtri-25d1a134)