Headroom

Name: Headroom
Author: chopratejas

headroom-ai · by chopratejas

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

77.0k 30.7k/wk 3 tools GitHub npm

No known CVEs

Apache-2.0 license

Actively maintained

Last commit 1d ago

Works with most clients

Transport: stdio, sse, http

3 tools · ~158 tok

Grade A · 0.1% of 200K ctx

MCPpedia last refreshed this data 1d ago

Edit this pageView history

Headroom is an MCP server that compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 95/100 on MCPpedia's security, maintenance and efficiency rubric.

Other

Step 1

Install in your client

Config is the same across clients - only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

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

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/headroom)](https://mcppedia.org/s/headroom)

Read me

What Headroom does

██╗ ██╗███████╗ █████╗ ██████╗ ██████╗ ██████╗ ██████╗ ███╗ ███╗ ██║ ██║██╔════╝██╔══██╗██╔══██╗██╔══██╗██╔═══██╗██╔═══██╗████╗ ████║ ███████║█████╗ ███████║██║ ██║██████╔╝██║ ██║██║ ██║██╔████╔██║ ██╔══██║██╔══╝ ██╔══██║██║ ██║██╔══██╗██║ ██║██║ ██║██║╚██╔╝██║ ██║ ██║███████╗██║ ██║██████╔╝██║ ██║╚██████╔╝╚██████╔╝██║ ╚═╝ ██║ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝╚═════╝ ╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═╝ The context compression layer for AI agents

Test This Server

This server supports HTTP transport. Be the first to test it - help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories - click any category to see the underlying evidence.

Score breakdown

95/100across 5 weighted dimensions

How we score →

0255075100

−5

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked headroom-ai against OSV.dev.

Inventory

Tools (3)

Click any tool to inspect its schema.

~158 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience - it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Headroom safe to use?: Headroom has no known CVEs as of the latest MCPpedia security scan. Authentication requirements were not detected automatically - check the project's documentation before connecting in a shared environment. Licensed under Apache-2.0.
How do I install Headroom?: Headroom supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can Headroom do?: Headroom provides 3 tools: headroom_compress, headroom_retrieve, headroom_stats. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Headroom?: Headroom is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Headroom actively maintained?: Headroom is actively maintained - last commit was 1 day ago. It has 77,048 GitHub stars.

Similar servers

Others in other

View all →

Awesome Agent Skills95

A curated list of skills, tools, tutorials, and capabilities for AI coding agents (Claude, Codex, Antigravity, Copilot, VS Code)

6.3k 12

System1 Agents95

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

166 8

MCP Wordpress Remote95

MCP WordPress Remote proxy server

186 10

Smart Drawio Next95

Generate, validate, repair and style editable draw.io XML diagrams.

366 13

MCP Security Weekly

Get CVE alerts and security updates for Headroom and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

What it does

Library — compress(messages) in Python or TypeScript, inline in any app.

Proxy — headroom proxy --port 8787, zero code changes, any language.

MCP server — headroom_compress, headroom_retrieve, headroom_stats for any MCP client.

Cross-agent memory — one shared store across Claude, Codex, Gemini and Grok, with automatic dedup.

headroom learn — mines failed sessions and writes corrections to CLAUDE.local.md (default, gitignored), CLAUDE.md, AGENTS.md, GEMINI.md or GROK.md.

Output token reduction — t

Frequently Asked Questions

Is Headroom safe to use?

Headroom has no known CVEs as of the latest MCPpedia security scan. Authentication requirements were not detected automatically - check the project's documentation before connecting in a shared environment. Licensed under Apache-2.0.

How do I install Headroom?

Headroom supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can Headroom do?

Headroom provides 3 tools: headroom_compress, headroom_retrieve, headroom_stats. See the full tools list on the server page for descriptions and parameters.

What AI clients work with Headroom?

Headroom is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is Headroom actively maintained?

Headroom is actively maintained - last commit was 1 day ago. It has 77,048 GitHub stars.

Quickstart · Headroom for Teams · Install · Proof · Agents · Docs · Discord · llms.txt

_{AI agents / LLMs: read /llms.txt here, or fetch
the live index ·
full docs blob.}

Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. Same answers, fraction of the tokens. Compression runs on your machine; no prompt or file content is sent anywhere to be compressed.

Headroom compressing a 10,144 token log dump to 1,260 tokens while preserving the FATAL line

_{10,144 → 1,260 tokens. The same FATAL found.}

What it does

Library — compress(messages) in Python or TypeScript, inline in any app.
Proxy — headroom proxy --port 8787, zero code changes, any language.
Agent wrap — headroom wrap claude|codex|grok|copilot|cursor|aider|opencode|cline|continue|goose|openhands|openclaw|vibe|omp|zcode in one command; undo with headroom unwrap <tool>.
MCP server — headroom_compress, headroom_retrieve, headroom_stats for any MCP client.
Cross-agent memory — one shared store across Claude, Codex, Gemini and Grok, with automatic dedup.
headroom learn — mines failed sessions and writes corrections to CLAUDE.local.md (default, gitignored), CLAUDE.md, AGENTS.md, GEMINI.md or GROK.md.
Output token reduction — t

... View full README on GitHub