A zero-touch, in-browser read of any MCP client config — what each server can reach, and what's worth reviewing before you connect. No install. No server is launched, no network is touched, nothing is stored.
Reads mcpServers (Claude Desktop / Cursor / Windsurf / Claude Code, plus per-project entries). Key names are read; values never are.
Static, config-only inference: what each server can reach (file, network, shell, destructive, exfiltration surface), plus config-health flags — remote endpoints, package-runner launches, credential-heavy entries, duplicate names.
A higher score means a broader surface to review and sandbox, not "dangerous." A filesystem server scoring high is expected. The findings list is the actionable part.
Without launching a server, only declared config is visible — scores skew low. The deep checks (prompt-injection in tool text, SSRF, the lethal trifecta, schema drift) need a connected scan. Run the CLI for those.
Your config is parsed in-memory for one request and never stored, logged, or sent anywhere else. Prefer fully local? The same engine ships as a CLI — run it offline.