MCPEngine is a production-grade implementation of the Model Context Protocol (MCP), providing standardized interfaces for large language models (LLMs). It supports functions such as OAuth authentication, resource management, and tool invocation, aiming to become the 'REST of the LLM world' framework.

PentestThinkingMCP is an automated penetration testing framework based on large language models and the MCP protocol. It can plan attack paths through Beam Search and MCTS algorithms, providing step reasoning, tool recommendation, and key path analysis for CTF, HTB, and real - world penetration testing.

A modular server project based on the MCP protocol that allows language models to call external tools (such as weather queries, dictionaries, mathematical calculations, etc.) in real-time to enable AI to interact with the real world.