mac-use
Native Mac Use for LLMs and MCP Servers.
hanzoai
README
mac-use
This project allows you to control macOS natively, providing direct system control through native macOS commands and utilities.
[!CAUTION] This comes with obvious risks. The Anthropic agent can control everything on your Mac. Please be careful.
Features
- Native macOS GUI interaction (no Docker required)
- Screen capture using native macOS commands
- Keyboard and mouse control through cliclick
- Multiple LLM provider support (Anthropic, Bedrock, Vertex)
- Streamlit-based interface
- Automatic screen resolution scaling
- File system interaction and editing capabilities
Prerequisites
- macOS Sonoma 15.7 or later
- Python 3.12+
- Homebrew (for installing additional dependencies)
- cliclick (
brew install cliclick
) - Required for mouse and keyboard control
Setup Instructions
- Clone the repository and navigate to it:
git clone https://github.com/hanzoai/mac-use.git
cd mac-use
- Create and activate a virtual environment:
python3.12 -m venv venv
source venv/bin/activate
- Run the setup script:
chmod +x setup.sh
./setup.sh
- Install Python requirements:
pip install -r requirements.txt
Running the Demo
Set up your environment and Anthropic API key
- In a
.env
file add:
API_PROVIDER=anthropic
ANTHROPIC_API_KEY=<key>
WIDTH=800
HEIGHT=600
DISPLAY_NUM=1
Set the screen dimensions (recommended: stay within XGA/WXGA resolution), and put in your key from Anthropic Console.
- Start the Streamlit app:
streamlit run streamlit.py
The interface will be available at http://localhost:8501
Screen Size Considerations
We recommend using one of these resolutions for optimal performance:
- XGA: 1024x768 (4:3)
- WXGA: 1280x800 (16:10)
- FWXGA: 1366x768 (~16:9)
Higher resolutions will be automatically scaled down to these targets to optimize model performance. You can set the resolution using environment variables:
export WIDTH=1024
export HEIGHT=768
streamlit run streamlit.py
[!IMPORTANT] The Beta API used in this reference implementation is subject to change. Please refer to the API release notes for the most up-to-date information.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.