A lightweight mcp to prevent poisoning CVE (CVE-2025-54136), researchers hijacking Claude Code/Copilot/Gemini via prompt injection, and hundreds of MCP servers exposed with zero auth, this mcp protects the individual developer's laptop, where most MCP servers actually run.
- capability exposure inferred + 4
- tool safety inferred + 12
- 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 →
- B · 16 → A · 13
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key
analyzed commit 47aeedc · analyzer v33 · 4d ago
danger signals1
- committed secret Anthropic key Sushank05-mcp-doorman-47aeedc/tests/redact.test.ts :51
sk-ant…(37 chars, redacted)
[](https://mcpobservatory.com/servers/github:Sushank05/mcp-doorman/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 Sushank05.