Multi-account MCP for Gmail, Calendar, Drive, Docs, and Sheets — 61 tools, token-efficient, macOS Keychain-backed
- capability exposureinferred+28
- tool safetyinferred+25
- trust mitigatorsmixed−3
inferredmixed
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 11m ago · see ecosystem CVEs →
No known CVEs for this server.
- highexfiltration combodrive_upload
single tool reads + sends: fs, net
- highexfiltration combodrive_comments_list
single tool reads + sends: fs, net
- hightoxic flow (lethal trifecta)drive_comments_list
single tool reads private data, ingests untrusted content, and reaches the network: fs, net
analyzed commit 909d074 · analyzer v18 · 3h ago
danger signals3
- over-broad OAuth scopehttps://www.googleapis.com/auth/driveadelaidasofia-google-workspace-mcp-909d074/accounts.py:47
"https://www.googleapis.com/auth/drive", - over-broad OAuth scopehttps://www.googleapis.com/auth/documentsadelaidasofia-google-workspace-mcp-909d074/accounts.py:48
"https://www.googleapis.com/auth/documents", - over-broad OAuth scopehttps://www.googleapis.com/auth/spreadsheetsadelaidasofia-google-workspace-mcp-909d074/accounts.py:49
"https://www.googleapis.com/auth/spreadsheets",
[](https://mcpobservatory.com/servers/github:adelaidasofia/google-workspace-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 adelaidasofia.