Cua: MCP Server – MCP.Bar

TL;DR: c/ua (pronounced "koo-ah", short for Computer-Use Agent) is a framework that enables AI agents to control full operating systems within high-performance, lightweight virtual containers. It delivers up to 97% native speed on Apple Silicon and works with any vision language models.

What is c/ua?

c/ua offers two primary capabilities in a single integrated framework:

High-Performance Virtualization - Create and run macOS/Linux virtual machines on Apple Silicon with near-native performance (up to 97% of native speed) using the Lume CLI with Apple's Virtualization.Framework.
Computer-Use Interface & Agent - A framework that allows AI systems to observe and control these virtual environments - interacting with applications, browsing the web, writing code, and performing complex workflows.

Why Use c/ua?

Security & Isolation: Run AI agents in fully isolated virtual environments instead of giving them access to your main system
Performance: Near-native performance on Apple Silicon
Flexibility: Run macOS or Linux environments with the same framework
Reproducibility: Create consistent, deterministic environments for AI agent workflows
LLM Integration: Built-in support for connecting to various LLM providers

System Requirements

Mac with Apple Silicon (M1/M2/M3/M4 series)
macOS 15 (Sequoia) or newer
Python 3.10+ (required for the Computer, Agent, and MCP libraries). We recommend using Conda (or Anaconda) to create an ad hoc Python environment.
Disk space for VM images (30GB+ recommended)

Quick Start

Option 1: Lume CLI Only (VM Management)

If you only need the virtualization capabilities:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"

For Lume usage instructions, refer to the Lume documentation.

Option 2: Full Computer-Use Agent Capabilities

If you want to use AI agents with virtualized environments:

Install the Lume CLI:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"

Pull the latest macOS CUA image:
```
lume pull macos-sequoia-cua:latest
```
Start Lume daemon service:
```
lume serve
```

Install the Python libraries:

pip install cua-computer cua-agent[all]

Use the libraries in your Python code:

from computer import Computer
from agent import ComputerAgent, LLM, AgentLoop, LLMProvider

async with Computer(verbosity=logging.DEBUG) as macos_computer:
  agent = ComputerAgent(
      computer=macos_computer,
      loop=AgentLoop.OPENAI, # or AgentLoop.ANTHROPIC, or AgentLoop.OMNI
      model=LLM(provider=LLMProvider.OPENAI) # or LLM(provider=LLMProvider.ANTHROPIC)
  )

  tasks = [
      "Look for a repository named trycua/cua on GitHub.",
  ]

  for task in tasks:
    async for result in agent.run(task):
      print(result)

Explore the Agent Notebook for a ready-to-run example.

Optionally, you can use the Agent with a Gradio UI:

from utils import load_dotenv_files
load_dotenv_files()
 
from agent.ui.gradio.app import create_gradio_ui

app = create_gradio_ui()
app.launch(share=False)

Option 3: Build from Source (Nightly)

If you want to contribute to the project or need the latest nightly features:

# Clone the repository
git clone https://github.com/trycua/cua.git
cd cua

# Open the project in VSCode
code ./.vscode/py.code-workspace

# Build the project
./scripts/build.sh

See our Developer-Guide for more information.

Monorepo Libraries

Library	Description	Installation
Lume	CLI for running macOS/Linux VMs with near-native performance using Apple's `Virtualization.Framework`.
Computer	Computer-Use Interface (CUI) framework for interacting with macOS/Linux sandboxes	`pip install cua-computer`
Agent	Computer-Use Agent (CUA) framework for running agentic workflows in macOS/Linux dedicated sandboxes	`pip install cua-agent`

Docs

For the best onboarding experience with the packages in this monorepo, we recommend starting with the Computer documentation to cover the core functionality of the Computer sandbox, then exploring the Agent documentation to understand Cua's AI agent capabilities, and finally working through the Notebook examples.

Demos

Demos of the Computer-Use Agent in action. Share your most impressive demos in Cua's Discord community!

MCP Server: Work with Claude Desktop and Tableau

AI-Gradio: multi-app workflow requiring browser, VS Code and terminal access

Notebook: Fix GitHub issue in Cursor

Accessory Libraries

Library	Description	Installation
Core	Core functionality and utilities used by other Cua packages	`pip install cua-core`
PyLume	Python bindings for Lume	`pip install pylume`
Computer Server	Server component for the Computer-Use Interface (CUI) framework	`pip install cua-computer-server`
SOM	Self-of-Mark library for Agent	`pip install cua-som`

Contributing

We welcome and greatly appreciate contributions to Cua! Whether you're improving documentation, adding new features, fixing bugs, or adding new VM images, your efforts help make lume better for everyone. For detailed instructions on how to contribute, please refer to our Contributing Guidelines.

Join our Discord community to discuss ideas or get assistance.

License

Cua is open-sourced under the MIT License - see the LICENSE file for details.

Microsoft's OmniParser, which is used in this project, is licensed under the Creative Commons Attribution 4.0 International License (CC-BY-4.0) - see the OmniParser LICENSE file for details.

Trademarks

Apple, macOS, and Apple Silicon are trademarks of Apple Inc. Ubuntu and Canonical are registered trademarks of Canonical Ltd. Microsoft is a registered trademark of Microsoft Corporation. This project is not affiliated with, endorsed by, or sponsored by Apple Inc., Canonical Ltd., or Microsoft Corporation.

Stargazers over time

Contributors

_f-trycua 💻	_{Pedro Piñera Buendía} 💻	_{Amit Kumar} 💻	_{Dung Duc Huynh (Kaka)} 💻	_{Zayd Krunz} 💻	_{Prashant Raj} 💻	_{Leland Takamine} 💻
_ddupont 💻	_{Ethan Gutierrez} 💻	_{Ricter Zheng} 💻	_{Rahul Karajgikar} 💻	_trospix 💻	_{Ikko Eltociear Ashimine} 💻	_{한석호(MilKyo)} 💻
_{Rahim Nathwani} 💻	_{Matt Speck} 💻