Chain of Thought

Exposes raw reasoning tokens from language models through Groq's API, allowing users to see the step-by-step thinking process within <think> tags before receiving final answers.

A Chain of Thought MCP server that exposes raw reasoning tokens from large language models through Groq's API. The server captures and streams the model's thinking process by intercepting content within <think> tags, allowing AI assistants to reveal their step-by-step reasoning before providing final answers. Built with FastMCP and supporting models like Qwen and DeepSeek, it enables more transparent AI interactions where users can see how the model arrives at conclusions rather than just receiving the final output.