📌Overview

Purpose: The Unity MCP Package aims to facilitate seamless communication between Unity and Large Language Models (LLMs) to automate workflows and enhance project capabilities.

Overview: The Unity MCP Server establishes a bidirectional communication channel between Unity and a Python server, enabling developers to programmatically manage assets, scenes, materials, and scripts within Unity, thus streamlining the development process.

Key Features:

• Bidirectional Communication: Enables effortless data exchange between Unity and LLMs, enhancing interactivity.

• Asset Management: Allows for the programmatic creation, importing, and manipulation of Unity assets, improving efficiency in project management.

• Scene Control: Provides tools for managing scenes and game objects, simplifying complex scene setups and changes.

• Material Editing: Facilitates easy modification of materials and their properties, allowing for quick visual adjustments.

• Script Integration: Supports viewing, creating, and updating C# scripts directly within Unity, promoting a streamlined coding experience.

• Editor Automation: Automates various Unity Editor functions, reducing repetitive tasks like building projects or testing environments.

---

Unity MCP Package

A Unity package that enables seamless communication between Unity and Large Language Models (LLMs) like Claude Desktop via the Model Context Protocol (MCP). This server acts as a bridge, allowing Unity to send commands to and receive responses from MCP-compliant tools.

Overview

The Unity MCP Server provides bidirectional communication between Unity and a Python server, enabling:

• Asset Management: Programmatically create, import, and manipulate Unity assets.
• Scene Control: Manage scenes, objects, and their properties.
• Material Editing: Modify materials and their properties.
• Script Integration: View, create, and update Unity scripts.
• Editor Automation: Control Unity Editor functions such as undo, redo, play, and build.

This project is ideal for developers looking to leverage LLMs to enhance Unity projects or automate repetitive tasks.

Installation

Ensure you have the following installed:

• Unity 2020.3 LTS or newer (currently only works in URP projects)
• Python 3.12 or newer
• uv package manager

Steps:

1. Install Python
   Download and install Python 3.12 or newer from python.org. Add Python to your system’s PATH during installation.

2. Install uv
   Use the command below based on your operating system:

   • Mac:

     brew install uv
     

   • Windows:

     powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
     

     Then, add uv to your PATH:

     set Path=%USERPROFILE%\.local\bin;%Path%
     

   • Linux:

     curl -LsSf https://astral.sh/uv/install.sh | sh
     

   Important: Do not proceed without installing uv.

3. Install the Unity Package

   1. Open Unity and go to Window > Package Manager.
   2. Click the + button and select Add package from git URL.
   3. Enter: https://github.com/justinpbarnett/unity-mcp.git

The Unity MCP Package will be available in your Unity project, and the server will start automatically when used with an MCP client.

Features

• Bidirectional Communication: Seamlessly send and receive data between Unity and LLMs.
• Asset Management: Import assets and create new prefabs programmatically.
• Scene Control: Open, save, and modify scenes.
• Material Editing: Apply and modify materials.
• Script Integration: Create and update C# scripts within Unity.
• Editor Automation: Automate Unity Editor tasks.

Contributing

To contribute:

1. Fork the Repository
   Fork github.com/justinpbarnett/unity-mcp.

2. Create a Branch

   git checkout -b feature/your-feature-name
   

   or

   git checkout -b bugfix/your-bugfix-name
   

3. Make Changes
   Implement your feature or fix.

4. Commit and Push
   Use clear, descriptive commit messages:

   git commit -m "Add feature: your feature description"
   git push origin feature/your-feature-name
   

5. Submit a Pull Request
   Open a pull request to the master branch.

License

This project is licensed under the MIT License. Feel free to use, modify, and distribute it as you see fit.

Troubleshooting

If you encounter issues:

• Unity Bridge Not Running: Ensure the Unity Editor is open and the MCP window is active. Restart Unity if needed.
• Python Server Not Connected: Confirm Python and uv are correctly installed.
• Configuration Issues: Ensure your MCP client is configured to communicate with the Unity MCP server.

For more help, visit the issue tracker or file a new issue.

Contact

For questions or discussions about the project, reach out on X: @justinpbarnett.

Acknowledgments

Thanks to everyone who has supported this project’s initial release, especially Unity Technologies for their Editor API. Enjoy integrating LLMs with Unity!