AgentSeal/awesome-mcp-security

Security scores for 800+ MCP servers. 9 analyzers scan for prompt injection, toxic flows, and attack surface risks. Updated daily. 🛡️

41
/ 100
Emerging

This project provides daily security assessments for over 800 MCP servers, helping AI agent developers and security teams understand the potential risks when integrating these servers into their AI agents. It takes the MCP server's public details and produces a security score and detailed findings, highlighting vulnerabilities like prompt injection risks or toxic data flows. The end user is primarily an AI agent developer or an AI security professional who needs to evaluate the safety of third-party MCP servers for use with their AI agents.

Use this if you are an AI agent developer or security team evaluating the security posture of MCP servers you plan to integrate with your AI agents, and you need quick, daily updated risk scores and reports.

Not ideal if you are looking for code quality assessments of the MCP server itself or seeking to secure a non-MCP-based system.

AI Agent Security Model Context Protocol (MCP) API Security Assessment AI Risk Management Prompt Engineering Security
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 11 / 25
Community 14 / 25

How are scores calculated?

Stars

15

Forks

3

Language

License

Last pushed

Mar 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/AgentSeal/awesome-mcp-security"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.