MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.

MCP - Shield is a security tool for scanning MCP server vulnerabilities, which can detect security risks such as tool poisoning attacks, data leakage channels, and cross - domain violations.

This project demonstrates MCP poisoning attacks against AI workflows, including verification of multiple attack scenarios such as code generation pollution and financial data leakage, for educational research purposes.

This project demonstrates a security vulnerability that enables remote code execution and data theft through MCP tool poisoning. It includes the implementation of a malicious server and an explanation of the attack principle, aiming for educational research.

This project focuses on experimenting with and analyzing tool poisoning techniques in a controlled environment, including environment setup, dependency installation, and experiment execution.