garagon/aguara
Security scanner for AI agent skills & MCP servers. 173 detection rules. 13 categories. 5 registries monitored daily. OpenClaw detection included. No API keys, no cloud, no LLM. One binary. Detection engine behind Oktsec.
Aguara is a security scanner designed for individuals and teams developing and deploying AI agent skills and Multi-Agent Collaboration Protocol (MCP) servers. It takes your agent skill files and MCP configurations as input and identifies potential security vulnerabilities like prompt injection, data exfiltration, and supply-chain attacks. The output is a detailed report indicating risks, helping security engineers and AI developers ensure their AI systems are safe before they go live.
Use this if you need to proactively scan AI agent skill files and MCP server configurations for security threats and vulnerabilities before they are deployed.
Not ideal if you're looking for a runtime protection solution, as this tool focuses on static analysis before deployment.
Stars
49
Forks
7
Language
Go
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/garagon/aguara"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Wh0am123/MCP-Kali-Server
MCP configuration to connect AI agent to a Linux machine.
DMontgomery40/pentest-mcp
NOT for educational purposes: An MCP server for professional penetration testers including...
BurtTheCoder/mcp-shodan
MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and...
cyproxio/mcp-for-security
MCP for Security: A collection of Model Context Protocol servers for popular security tools like...
0x4m4/hexstrike-ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot,...