Personal-use MCP server that gives Microsoft 365 Copilot real hands on your own laptop: files, Python, Office, SQL, Web. 100+ tools, autonomous relay, easily extensible, no extra licences.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 5
- trust mitigators mixed − 3
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.
grade last moved 1w ago · see ecosystem CVEs →
- C · 49 → C · 57
- C · 37 → C · 49
- C · 57 → C · 37
- D · 60 → C · 57
- C · 52 → D · 60
- A · 0 → C · 52
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec(), __import__ sink
analyzed commit 5a1c787 · analyzer v33 · 12h ago
danger signals3
- dynamic code execution eval()/exec() MasayukiTa-m365-copilot-companion-mcp-5a1c787/bench/eval_one.py :33
exec(compile(program, "<bench>", "exec"), ns) - dynamic code execution __import__ sink MasayukiTa-m365-copilot-companion-mcp-5a1c787/relay/selfimprove/test_authority_ledger.py :186
assert __import__("os").path.isfile(store) - dynamic code execution eval()/exec() MasayukiTa-m365-copilot-companion-mcp-5a1c787/tests/test_faulthandler_rotation.py :44
cap = eval(m.group(1), {"__builtins__": {}})
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:MasayukiTa/m365-copilot-companion-mcp/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 MasayukiTa.