Mirror Mcp

Mirror Mcp is an open-source Model Context Protocol (MCP) server that equips large language models (LLMs) with self-reflection and introspection capabilities. By providing a `reflect` tool, it enables LLMs to ask themselves questions and iteratively analyze or critique their own reasoning, leveraging MCP's sampling and context management. Designed for developers and AI researchers, Mirror Mcp aims to improve AI reliability, confidence calibration, and iterative problem-solving.