MCP server for Google Workspace with progressive context disclosure and multi-account orchestration
- capability exposure inferred + 35
- trust mitigators mixed − 16
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 2d ago · see ecosystem CVEs →
- B · 24 → B · 19
- A · 0 → B · 24
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed v4.0.1 · analyzer v33 · 4w ago
danger signals4
- over-broad OAuth scope gmail.modify package/build/accounts/oauth.js :11
gmail: ['https://www.googleapis.com/auth/gmail.modify'], - over-broad OAuth scope https://www.googleapis.com/auth/drive package/build/accounts/oauth.js :12
drive: ['https://www.googleapis.com/auth/drive'], - over-broad OAuth scope https://www.googleapis.com/auth/spreadsheets package/build/accounts/oauth.js :14
sheets: ['https://www.googleapis.com/auth/spreadsheets'], - over-broad OAuth scope https://www.googleapis.com/auth/documents package/build/accounts/oauth.js :15
docs: ['https://www.googleapis.com/auth/documents'],
[](https://mcpobservatory.com/servers/npm:@aaronsb/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 aaronsb.