medusa

by Pantheon-Security · MCP 服务器 · ★ 595

About medusa

🐍 MEDUSA - AI Security Scanner AI-first security scanner with 40,000+ detection patterns for AI/ML, agents, and LLM applications. 🤖 Works out of the box - no tool installation required. 🚨 200 CVEs: Log4Shell, Spring4Shell, XZ Utils, LangChain RCE, MCP-Remote RCE, React2Shell 🔥 — Scan any repo for AI supply chain attacks (repo poisoning, prompt injection, MCP tool poisoning) 🔐 — Find leaked API keys in your Claude / Cursor / Copilot / shell

agent-securityai-securitycode-analysiscve-detectiondevsecopsllm-securitymcpnextjsopen-sourcepython

Quick Facts

Stars595
Forks108
LanguagePython
CategoryMCP 服务器
LicenseAGPL-3.0
Quality Score37.9/100
Open Issues2
Last Updated2026-06-10
Created2025-11-15
Platformsmcp, python
Est. Tokens~2155k

More MCP 服务器 Tools

Explore other popular mcp 服务器 tools:

View all MCP 服务器 tools →

Popular Python Agent Tools

Frequently Asked Questions

What is medusa?

medusa is AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo. It is categorized as a MCP 服务器 with 595 GitHub stars.

What programming language is medusa written in?

medusa is primarily written in Python. It covers topics such as agent-security, ai-security, code-analysis.

How do I install or use medusa?

You can find installation instructions and usage details in the medusa GitHub repository at github.com/Pantheon-Security/medusa. The project has 595 stars and 108 forks, indicating an active community.

What license does medusa use?

medusa is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse MCP 服务器 tools