Python · MIT
graygnatconsole/mcp-audit-tool
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.
★ 544
Stars
4 forks · 1 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
22.0
Momentum / 100
see the breakdown below
43d ago
Created
last push 14d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.0 | last push 14d ago; decays to zero at 180 days |
| Scale | 15 | 7.9 | 544 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 22.0 | capped at 35 because growth is unmeasured |
Detail
| Topics | agent-securityagentic-aiai-securitycursorllm-guardrailsllm-securitymcpmcp-auditmcp-scannermcp-securitymcp-servermcp-server-pythonmodel-context-protocolprompt-injectionsecurity-scannersupply-chainsupply-chain-securitytool-poisoningvulnerability-scanner |
| Matched on | AI Agents (agentic-ai) Agent Skills & MCP (mcp, model-context-protocol) |
| Short window | +0 stars over 9 days = 0.0/day |
| Long window | +353 stars over 26 days = 13.6/day |
| Lifetime average | 13.47 stars/day over 40 days |
| First seen here | 2026-10-11 |
| Last read | 11d ago |