humanMCP — kapoost
io.github.kapoost/humanmcp · v0.3.0 · 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
Personal MCP server for humans who create. Proof of authorship, license control.
Source: https://github.com/kapoost/humanmcp-go
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 43 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_skill). Require confirmation before the agent calls them. |
What was checked
- https://kapoost.humanmcp.net/mcp: answers without auth
Public tools: about_humanmcp, ask_human, bootstrap_session, delete_skill, fetch_answer, fetch_narada_result, get_author_profile, get_certificate, get_persona, get_persona_journal, get_skill, leave_comment, leave_message, list_blobs, list_collection, list_content, list_personas, list_provenance, list_skill_groups, list_skills, load_skill_group, mysloodsiewnia_get, mysloodsiewnia_list, mysloodsiewnia_search, mysloodsiewnia_status, mysloodsiewnia_write, prepare_narada, read_blob, read_collection_item, read_content
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-kapoost-humanmcp-601b58d0)