headroom Model Context Protocol (MCP) Server

GitHub

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers.

66,105 stars

Python 1 file · ~1,374 tokens #agent #ai #anthropic #claude-code #compression #context-engineering #context-window #cursor

headroom MCP Server

MCP server for headroomlabs-ai/headroom

Ready-to-Use Client Configurations

{
  "mcpServers": {
    "headroom": {
      "command": "npx",
      "args": [
        "-y",
        "@headroomlabs-ai/headroom"
      ]
    }
  }
}

{
  "mcpServers": {
    "headroom": {
      "command": "npx",
      "args": [
        "-y",
        "@headroomlabs-ai/headroom"
      ]
    }
  }
}

{
  "mcpServers": {
    "headroom": {
      "command": "npx",
      "args": [
        "-y",
        "@headroomlabs-ai/headroom"
      ]
    }
  }
}

{
  "mcpServers": {
    "headroom": {
      "command": "npx",
      "args": [
        "-y",
        "@headroomlabs-ai/headroom"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

{
  "mcpServers": {
    "headroom": {
      "command": "npx",
      "args": [
        "-y",
        "@headroomlabs-ai/headroom"
      ]
    }
  }
}

docker run -i --rm mcp/headroom