Mcpcheck — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcpcheck (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.
A webcheck.xyz-style scanner for remote MCP servers.
Enter the URL of an MCP server (Streamable HTTP or SSE transport) and get a dashboard of checks:
npm install
npm run devOpen http://localhost:3000 and paste an MCP server URL to scan.
http:// and https:// targets are accepted; scanning private/internal IP ranges or localhost is blocked to prevent SSRF.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.