Open security scoring
Should you connect
that MCP server?
try
Trust grade and a separate capability rating for any Model Context Protocol (MCP) server, against a published, open-source policy. It reports what an outside observer can check, and does not certify that a server is safe.
Beta. Policy v0.2, checks still being tuned. Read a grade as a reason to look closer.
What the checks look at
| § | Area | Method |
|---|---|---|
| §1 | Provenance | Registry listing, repository health, package and repo consistency, npm provenance attestation. |
| §2 | Capabilities | Tool surface read via tools/list or static source analysis. Untrusted code is never executed. Shell, filesystem, egress, and credential access are flagged. |
| §3 | Transport & auth | HTTPS, authentication required, OAuth 2.1 protected-resource metadata (June 2025 spec). |
| §4 | Vulnerabilities | Known advisories via OSV.dev, where a checkable package exists. |
| §5 | Instruction integrity | Hidden instructions, zero-width characters, cross-tool shadowing, and authority over-reach across tool descriptions, initialize instructions, prompts, and resources. Schema changes between scans are flagged as a rug-pull signal. |