Model Context Protocol (MCP) server for Google Sheets (read + write) with per-user Google OAuth, a write allowlist, and audit logging.
- capability exposureinferred+24
- tool safetyinferred+12
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 14m ago · see ecosystem CVEs →
- C · 48 → C · 36
- B · 34 → C · 48
No known CVEs for this server.
- highexfiltration combocreate_spreadsheet
single tool reads + sends: fs, net
analyzed commit 507f039 · analyzer v18 · 4h ago
danger signals1
- over-broad OAuth scopehttps://www.googleapis.com/auth/spreadsheetsmicahyee415-google-sheets-mcp-507f039/src/index.ts:96
scopes_supported: ["openid", "email", "profile", "https://www.googleapis.com/auth/spreadsheets", "https://www.googleapis.com/auth/drive.readonly"],
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 micahyee415.