Simulate security vulnerabilities within an MCP (Model Context Protocol) environment for research and testing.
This project is an intentionally vulnerable MCP application built for security research. It combines FastAPI, SQLite, and Ollama LLM to create a system that routes natural language input to either SQL queries or shell commands. The app is designed to be susceptible to SQL Injection (SQLi) and Remote Code Execution (RCE) vulnerabilities via FastAPI, JSON-RPC, and LLM-based decision logic. It is intended for use in isolated environments, CTFs, or research labs only, and should NEVER be used in production.