# headroom

> MCP Server

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

## Overview

- **Category:** AI
- **Language:** Python
- **Stars:** 66444
- **Forks:** 1895
- **Owner:** chopratejas
- **GitHub:** https://github.com/chopratejas/headroom
- **Homepage:** https://headroom-docs.vercel.app/docs
- **Created:** 2026-01-07T19:58:51+00:00
- **Updated:** 2026-06-15T07:46:19+00:00
- **Source:** https://model-context-protocol.com/servers/headroom

## Related Articles

- [headroom MCP Server: 95% Token Compression for LLMs](https://model-context-protocol.com/blog/headroom-mcp-server-95-token-compression-for-llms-mcp-server-guide)