OSS Radar
graygnatconsole/mcp-audit-tool
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets… Why it matters: extends what MCP-compatible assistants can connect to and do.
GitHub description: 🛡️ 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.
Stars
274
Last 24h
+6
Last 7 days
+42est.
Forks
5
Who it's for
- 12 built-in detection rules covering the OWASP MCP Top 10 categories: tool poisoning, rug pulls, secrets exposure, command injection, instal
- Zero-config auto-discovery — finds Claude Desktop, Cursor, Windsurf, Cline, Zed, and VS Code MCP configs on macOS, Linux, and Windows automa
- Security score & grade (A+ → F) with clear, actionable remediation for every finding
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Daily, since Oct 13, 2026 · 268 → 274
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/graygnatconsole/mcp-audit-tool)<a href="https://ossradar.net/repo/graygnatconsole/mcp-audit-tool"><img src="https://ossradar.net/badge/graygnatconsole/mcp-audit-tool" alt="Trending on OSS Radar"></a>About mcp-audit-tool
graygnatconsole/mcp-audit-tool is a Python project in the MCP category, created 18 days ago. It has 274 GitHub stars and 5 forks, and gained +42 stars over the last 7 days (early estimate), ranking #28 of 37 MCP repos tracked by OSS Radar this week.
See more trending MCP repos or the top AI repos this week. Looking for something similar? See mcp-audit-tool alternatives.
- Language
- Python
- Category
- MCP
- Created
- Sep 26, 2026
- Last code push
- 17 days ago (Sep 26, 2026)
- Latest release
- No releases yet
- agent-security
- agentic-ai
- ai-security
- cursor
- llm-guardrails
- llm-security
- mcp
- mcp-audit
- mcp-scanner
- mcp-security
- mcp-server
- mcp-server-python
- model-context-protocol
- prompt-injection
- security-scanner
- supply-chain
- supply-chain-security
- tool-poisoning
- vulnerability-scanner
Similar rising repos
- NVIDIA/SkillSpector+70est.
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and… Why it matters: useful plumbing for shipping LLM-powered features.
- DeusData/codebase-memory-mcp+77est.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. Why it matters: extends what MCP-compatible assistants can connect to and do.
- 1105216375-alt/resimind+100est.
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Why it matters: extends what MCP-compatible assistants can connect to and do.
- scaleapi/agentenv-framework+35est.
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions… Why it matters: extends what MCP-compatible assistants can connect to and do.
🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports… Why it matters: extends what MCP-compatible assistants can connect to and do.
- skillmds/skillmd+35est.
Lint, search, and install Agent Skills (SKILL.md) — CLI + MCP server + lint engine. Why it matters: extends what MCP-compatible assistants can connect to and do.