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. Library, proxy, MCP server.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"headroom": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-headroom"
]
}
}
}