Free lite version of MCP Security Auditor Claude Skill — audit MCP servers on 3 dimensions. Full version: apexstack.gumroad.com/l/mcp-security-auditor
SaferSkills independently audited mcp-security-auditor-lite (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 your MCP server deployments for security vulnerabilities. Scan for tool description injection, permission scope issues, and supply chain risks.
.skill file from this repo| Feature | Lite (Free) | Full ($19) |
|---|---|---|
| Tool Description Integrity | ✅ | ✅ |
| Permission Scope Analysis | ✅ | ✅ |
| Supply Chain Risk | ✅ | ✅ |
| Server Auth & Transport | ❌ | ✅ |
| Tool Registry Integrity | ❌ | ✅ |
| Cross-Tool Interaction Safety | ❌ | ✅ |
| Config Management | ❌ | ✅ |
| Logging & Observability | ❌ | ✅ |
| Injection Scanner | ❌ | ✅ |
| Permission Analyzer | ❌ | ✅ |
| Config Drift Detector | ❌ | ✅ |
| Monitoring Checklist | ❌ | ✅ |
[Get the full MCP Security Auditor →](https://apexstack.gumroad.com/l/mcp-security-auditor)
Built by Apex Stack — security and automation tools for developers deploying AI agents.
Topics: claude-skills mcp security ai-agents devsecops
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.