AIS2Lab/MCPSecBench

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols

43
/ 100
Emerging

Implements adversarial attack scenarios (tool poisoning, DNS rebinding, man-in-the-middle, server name squatting) against MCP implementations through instrumented malicious servers and clients. Supports automated testing across Claude, OpenAI, and Cursor via configurable attack scripts that can optionally apply defenses like MCIP and AIM-MCP protection. Evaluates vulnerabilities through both CLI interaction and desktop application integration with configurable prompts and real-time UI automation.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 17 / 25

How are scores calculated?

Stars

30

Forks

8

Language

Python

License

MIT

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/AIS2Lab/MCPSecBench"

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