Comprehensive Home Assistant MCP Server with 60 tools for AI-driven smart home control including SSH/SFTP file management. Production-ready k3s deployment for Pi4 cluster.
- capability exposure inferred + 22
- recent drift inferred + 20
- tool safety inferred + 5
- trust mitigators mixed − 8
inferred mixed
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 1m ago · see ecosystem CVEs →
- B · 31 → C · 39
- B · 34 → B · 31
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec(), __import__()
analyzed commit 99955a9 · analyzer v28 · 1d ago
danger signals2
- dynamic code execution eval()/exec() agarib-homeassistant-mcp-server-99955a9/ha-openapi-server/app/routers/code_execution.py :70
exec(request.code, safe_globals) - dynamic code execution __import__() agarib-homeassistant-mcp-server-99955a9/ha-openapi-server/server.py :29
__import__(lib)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:agarib/homeassistant-mcp-server/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 agarib.