The Unsloth MCP Server is a server for efficiently fine-tuning large language models. Through optimized algorithms and 4-bit quantization technology, it achieves a 2-fold increase in training speed and an 80% reduction in video memory usage, supporting multiple mainstream models.

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.