An intentionally vulnerable MCP server for security training, enabling users to practice attacking and defending AI agents through realistic scenarios.
An educational project that deliberately implements vulnerable MCP servers to demonstrate various security risks like prompt injection, tool poisoning, and code execution for training security researchers and AI safety professionals.
A deliberately insecure MCP server for practicing penetration testing, featuring 26 challenges at three difficulty levels with flags to capture, covering vulnerabilities like RCE, SSRF, SQLi, and more.
A deliberately vulnerable MCP server for practicing exploitation of tool poisoning, command injection, and path traversal. Includes fixed versions and an agent demo to reproduce the issues in a controlled environment.
IMCP - Insecure Model Context Protocol The DVWA for AI Security! Welcome to IMCP – a deliberately vulnerable framework that exposes 16 critical security weaknesses in AI/ML systems. Whether you're a security researcher, developer, or educator, IMCP is your playground for hands-on learning about real