README

🤖 Computer Use MCP that controls your entire desktop

Give AI assistants (Claude, Cursor, VS Code, etc.) the ability to control your desktop and automate tasks across any application.

Claude Code (one-liner):

bash

claude mcp add computeruse "npx -y computeruse-mcp-agent@latest"

Other clients (Cursor, VS Code, Windsurf, etc.):

Add to your MCP config file:

json

{
  "mcpServers": {
    "computeruse-mcp-agent": {
      "command": "npx",
      "args": ["-y", "computeruse-mcp-agent@latest"],
      "env": {
        "LOG_LEVEL": "info",
        "RUST_BACKTRACE": "1"
      }
    }
  }
}

See the MCP Agent README for detailed setup instructions.

Why ComputerUse MCP?

Uses your browser session - no need to relogin, keeps all your cookies and auth
Doesn't take over your cursor or keyboard - runs in the background without interrupting your work
Works across all dimensions - pixels, DOM, and Accessibility tree for maximum reliability

Use Cases

Create a new instance on GCP, connect to it using CLI
Check logs on Vercel to find most common errors
Test my app new features based on recent commits

🚀 What's new

01/09/26 - Mediar IDE (Cursor for Windows automation) is in public access - download now
10/30 Public alpha is live - Cursor for Windows automation
09/26 ComputerUse was on Cohere Labs podcast, also check the slides
08/25 Big release — NodeJS SDK in YAML workflows, run JS in browser, OS event recording → YAML generation in MCP, and more
08/25 we raised $2.8m to give AI hands to every desktop

🧠 Why ComputerUse

For Developers

Create automations that work across any desktop app or browser
Runs 100x faster than ChatGPT Agents, Claude, Perplexity Comet, BrowserBase, BrowserUse (deterministic, CPU speed, with AI recovery)
95% success rate unlike most computer use overhyped products
MIT-licensed — fork it, ship it, no lock-in

We achieve this by pre-training workflows as deterministic code, and calling AI only when recovery is needed.

For Teams

Our public beta workflow builder + managed hosting:

Record, map your processes, and implement the workflow without technical skills
Deploy AI to execute them at >95% success rate without managing hundreds of Windows VMs
Kill repetitive work without legacy RPA complexity, implementation and maintenance cost

Feature Support

ComputerUse supports Windows, macOS, and Linux.

Feature	Windows	macOS	Linux	Notes
Core Automation
Element Locators	✅	✅	✅	Find elements by `name`, `role`, `window`, etc.
UI Actions (`click`, `type`)	✅	✅	✅	Core interactions with UI elements.
Application Management	✅	✅	✅	Launch, list, and manage applications.
Window Management	✅	✅	✅	Get active window, list windows.
Advanced Features
Browser Automation	✅	✅	✅	Chrome extension enables browser control.
Workflow Recording	✅	🟡	🟡	Record human workflows for deterministic automation.
Monitor Management	✅	✅	✅	Multi-display support.
Screen & Element Capture	✅	✅	✅	Take screenshots of displays or elements.
Libraries
Python (`computeruse.py`)	🟡	🟡	🟡	`pip install computeruse`
TypeScript (`@elizaos/computeruse`)	✅	✅	✅	`npm i @elizaos/computeruse`
Workflow (`@mediar-ai/workflow`)	✅	🟡	🟡	`npm i @mediar-ai/workflow`
CLI (`@mediar-ai/cli`)	✅	✅	✅	`npm i @mediar-ai/cli`
KV (`@mediar-ai/kv`)	✅	✅	✅	`npm i @mediar-ai/kv`
MCP (`computeruse-mcp-agent`)	✅	✅	✅	`npx -y computeruse-mcp-agent --add-to-app [app]`
Rust (`computeruse-rs`)	✅	✅	✅	`cargo add computeruse-rs`

Legend:

✅: Supported - The feature is stable and well-tested.
🟡: Partial / Experimental - The feature is in development and may have limitations.
❌: Not Supported - Not available on this platform.

Platform Notes:

macOS: Requires Accessibility permissions (System Preferences → Privacy & Security → Accessibility)
Linux: Requires AT-SPI2 (enabled by default on GNOME/KDE). For X11, install wmctrl and xdotool.

🕵️ How to Inspect Accessibility Elements (like `name:Seven`)

To create reliable selectors (e.g. name:Seven, role:Button, window:Calculator), you need to inspect the Windows Accessibility Tree:

Windows

Tool: Accessibility Insights for Windows
Alt: Inspect.exe (comes with Windows SDK)
Usage: Open the app you want to inspect → launch Accessibility Insights → hover or use keyboard navigation to explore the UI tree (Name, Role, ControlType, AutomationId).

macOS

Tool: Accessibility Inspector (included with Xcode)
Alt: osascript -e 'tell application "System Events" to entire contents of window 1 of application process "Safari"'
Usage: Open Xcode → Developer Tools → Accessibility Inspector. Select the target process and inspect elements' AXRole, AXTitle, AXIdentifier attributes.
Requirement: Grant Accessibility permissions to your automation script/terminal (System Preferences → Privacy & Security → Accessibility).

Linux (Experimental)

Tool: Accerciser (GNOME Accessibility Inspector)
Install: sudo apt install accerciser or sudo dnf install accerciser
Usage: Open Accerciser → navigate the AT-SPI tree to find element names, roles, and states.

These tools show you the Name, Role, ControlType, and other metadata used in ComputerUse selectors.

Platform Support

Platform	CLI	MCP Agent	Automation	Installation Method
Windows	✅	✅	✅	npm/bunx
macOS	✅	✅	✅	npm/bunx (requires Accessibility permissions)
Linux	✅	✅	✅	npm/bunx (requires AT-SPI2, wmctrl/xdotool)

Note:

macOS requires Accessibility permissions for your terminal/app
Linux requires AT-SPI2 (default on GNOME/KDE) and wmctrl/xdotool for X11 window management

Troubleshooting

For detailed troubleshooting, debugging, and MCP server logs, send us a message.

Contributing

Contributions are welcome! Please feel free to submit issues and pull requests. many parts are experimental, and help is appreciated.