Local MCP server with safe tools for files, Git, browser checks, prompt improvement, skill routing, Notion, Obsidian, RAG, and personal AI workflows.
- capability exposure inferred + 35
- tool safety inferred + 24
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 3m ago · see ecosystem CVEs →
- C · 47 → C · 59
- C · 42 → C · 47
- C · 47 → C · 42
- B · 34 → C · 47
- B · 24 → B · 34
- B · 34 → B · 24
- C · 46 → B · 34
- C · 50 → C · 46
No known CVEs for this server.
- high tool shadowing run_command
tool "run_command" shadows a verified server's tool
- medium exfiltration combo find_api_files
single tool reads + sends: fs, net
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low dangerous code
env-secret-flows-to-network-py: An environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/scratch/obs-code-mI47Mk/ntaffzii-ai-desk
- low exfiltration combo check_github_api_auth
single tool reads + sends: net, secrets
[](https://mcpobservatory.com/servers/github:ntaffzii/ai-desk-tools/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of ntaffzii.