mcp-scorecard — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mcp-scorecard (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Audit any MCP server for agent-readiness — get a 0–100 score across 10 checks with the exact fixes. Local-first, zero credentials.
npx -y mcp-scorecard <target><target>: a published npm package, a GitHub repo URL, or a local dist/index.js.--json — structured output for CI / piping.--min-score 80 — exit non-zero if the score drops below a threshold (CI gate).manifest discoverability · tool naming · tool descriptions · schema validity · annotations · mutation gating · privacy modes · resources · agent manifest · smoke test.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.