munim-computer-use

<!-- Banner Image -->

<p align="center">
  <a href="https://github.com/munimtechnologies/munim-computer-use">
    <img alt="Munim Technologies Computer Use" height="128" src="./.github/resources/banner.png?v=1">
    <h1 align="center">munim-computer-use</h1>
  </a>
</p>

<p align="center">
  <a aria-label="Latest release" href="https://github.com/munimtechnologies/munim-computer-use/releases/latest" target="_blank">
    <img alt="Latest release" src="https://img.shields.io/github/v/release/munimtechnologies/munim-computer-use?style=flat-square&label=Version&labelColor=000000&color=0066CC" />
  </a>
  <a aria-label="License" href="https://github.com/munimtechnologies/munim-computer-use/blob/main/LICENSE" target="_blank">
    <img alt="License: Apache-2.0" src="https://img.shields.io/badge/License-Apache%202.0-success.svg?style=flat-square&color=33CC12" />
  </a>
  <a aria-label="package downloads" href="https://www.npmtrends.com/munim-computer-use" target="_blank">
    <img alt="Downloads" src="https://img.shields.io/npm/dm/munim-computer-use.svg?style=flat-square&labelColor=gray&color=33CC12&label=Downloads" />
  </a>
  <a aria-label="total package downloads" href="https://www.npmjs.com/package/munim-computer-use" target="_blank">
    <img alt="Total Downloads" src="https://img.shields.io/npm/dt/munim-computer-use.svg?style=flat-square&labelColor=gray&color=0066CC&label=Total%20Downloads" />
  </a>
  <a aria-label="MCP" href="https://modelcontextprotocol.io" target="_blank">
    <img alt="MCP stdio server" src="https://img.shields.io/badge/MCP-stdio%20server-8A2BE2?style=flat-square" />
  </a>
  <img alt="Platforms" src="https://img.shields.io/badge/Platforms-macOS%20%7C%20Windows%20%7C%20Linux-lightgrey?style=flat-square" />
</p>

<p align="center">
  <a aria-label="download" href="https://github.com/munimtechnologies/munim-computer-use/releases/latest"><b>Download</b></a>
&ensp;•&ensp;
  <a aria-label="documentation" href="https://github.com/munimtechnologies/munim-computer-use#readme">Read the Documentation</a>
&ensp;•&ensp;
  <a aria-label="report issues" href="https://github.com/munimtechnologies/munim-computer-use/issues">Report Issues</a>
&ensp;•&ensp;
  <a aria-label="website" href="https://munimtech.com/computer-use">munimtech.com/computer-use</a>
</p>

<h6 align="center">Follow Munim Technologies</h6>
<p align="center">
  <a aria-label="Follow Munim Technologies on GitHub" href="https://github.com/munimtechnologies" target="_blank">
    <img alt="Munim Technologies on GitHub" src="https://img.shields.io/badge/GitHub-222222?style=for-the-badge&logo=github&logoColor=white" />
  </a>&nbsp;
  <a aria-label="Follow Munim Technologies on LinkedIn" href="https://linkedin.com/in/sheehanmunim" target="_blank">
    <img alt="Munim Technologies on LinkedIn" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
  </a>&nbsp;
  <a aria-label="Visit Munim Technologies Website" href="https://munimtech.com" target="_blank">
    <img alt="Munim Technologies Website" src="https://img.shields.io/badge/Website-0066CC?style=for-the-badge&logo=globe&logoColor=white" />
  </a>
</p>

## Introduction

**Computer Use** is an open-source [MCP](https://modelcontextprotocol.io) server — a computer-use agent (CUA) backend — that lets any coding agent use your computer the way a person does. It reads the screen through accessibility trees, clicks and types **in the background** so your mouse stays yours, shows an agent pointer where it is working, zooms in on small text, and drives tabs in your signed-in Chrome — on **macOS, Windows and Linux**.

**Works with Claude Code, Codex, Cursor and [MT Code](https://munimtech.com/mt-code)**, or any other MCP client, with any model — no vision model is required for interaction.

**Built by [Munim Technologies](https://munimtech.com/computer-use)** as the Computer Use engine of MT Code, and published here on its own.

## Table of contents

- [Quick start](#quick-start)
- [Capability matrix](#capability-matrix)
- [Why it works well](#why-it-works-well)
- [Tools](#tools-26)
- [Repository layout](#repository-layout)
- [Environment flags](#environment-flags)
- [Prompting your agent](#prompting-your-agent)
- [Contributing](#contributing)
- [Credits and license](#credits-and-license)

## Quick start

1. Download the latest binary for your platform from [Releases](https://github.com/munimtechnologies/munim-computer-use/releases/latest) (`munim-computer-use-macos-universal.zip`, `munim-computer-use-windows-x64.zip`) or [build from source](#build-from-source).
2. Put it somewhere on your `PATH` (`/usr/local/bin/munim-computer-use`, or `%LOCALAPPDATA%\Programs\munim-computer-use\munim-computer-use.exe`).
3. macOS only: run `munim-computer-use request-permissions` once to be prompted for Accessibility and Screen Recording.
4. Register it with your agent:

```sh
# Claude Code — fastest: the npm launcher fetches the signed binary on first run
claude mcp add munim-computer-use -- npx -y munim-computer-use
# or point at a downloaded binary
claude mcp add munim-computer-use -- /usr/local/bin/munim-computer-use
```

```toml
# Codex — ~/.codex/config.toml
[mcp_servers.munim-computer-use]
command = "npx"
args = ["-y", "munim-computer-use"]
```

```json
// Cursor — .cursor/mcp.json
{ "mcpServers": { "munim-computer-use": { "command": "npx", "args": ["-y", "munim-computer-use"] } } }
```

Then ask: _"Open Safari, find the cheapest flight to Denver on Tuesday and put it in a note."_ The agent reads the UI with `get_app_state`, acts by element id, and verifies with `screenshot`.

## Capability matrix

**Munim Computer Use** is the highlighted first column; the others are the computer-use servers people reach for. each cell comes from that project's own README in September 2026 (sources under [Credits and license](#credits-and-license)). ✅ present · ❌ absent or not documented · ⚠️ partial.

| Capability                                  | **Munim Computer Use** | Codex Computer Use | Anthropic reference demo | Windows-MCP | MacOS-MCP | open-computer-use | computer-use-mcp (zavora) | Notes                                                                                                                                                                                                                                           |
| ------------------------------------------- | ---------------------- | ------------------ | ------------------------ | ----------- | --------- | ----------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| macOS                                       | **✅**                 | ✅                 | ❌                       | ❌          | ✅        | ✅                | ✅                        | The Anthropic demo drives a Linux desktop inside Docker, not your machine.                                                                                                                                                                      |
| Windows                                     | **✅**                 | ✅                 | ❌                       | ✅          | ❌        | ✅                | ✅                        | Windows-MCP is Windows only; MacOS-MCP is macOS only.                                                                                                                                                                                           |
| Linux                                       | **✅**                 | ❌                 | ✅ (sandbox)             | ❌          | ❌        | ✅                | ✅                        | Munim Computer Use uses AT-SPI + X11; native Wayland apps get element actions but not coordinate clicks.                                                                                                                                        |
| Accessibility tree with element ids         | **✅**                 | ❌                 | ❌                       | ✅          | ✅        | ✅                | ✅                        | Codex and the Anthropic demo are screenshot-driven. Ids let the agent press _the button_ instead of a pixel.                                                                                                                                    |
| Background input (your mouse never moves)   | **✅**                 | ✅                 | n/a                      | ❌          | ❌        | ❌                | ❌                        | Munim Computer Use addresses events to the target window (SkyLight on macOS, posted window messages on Windows, XTEST on Linux). Codex does this too, with a second cursor of its own. Every other server in this table drives the real cursor. |
| Agent pointer overlay                       | **✅**                 | ✅                 | ❌                       | ⚠️          | ❌        | ❌                | ❌                        | Windows-MCP flashes a border around captures; Codex draws its own cursor on your screen.                                                                                                                                                        |
| Zoom into a region at full resolution       | **✅**                 | ❌                 | ✅                       | ❌          | ❌        | ❌                | ❌                        | Anthropic's toolset has `zoom`; here it is a tool on every platform.                                                                                                                                                                            |
| Screenshots carry screen-coordinate mapping | **✅**                 | n/a                | n/a                      | ❌          | ❌        | ❌                | ❌