MCP Unity

by CoderGamester
Verified

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Integrations

  • Runs the MCP server using Node.js, creating a bridge between AI assistants and the Unity Editor.

  • Uses WebSocket communication to connect the Unity Editor with the Node.js MCP server, enabling real-time interaction between AI agents and Unity.

  • Implements the server-side MCP protocol in TypeScript, providing type-safe communication between AI agents and Unity.

MCP Unity

,/(/. *(/, */(((((/. *((((((*. .*((((((((((/. *((((((((((/. ./((((((((((((((/ *((((((((((((((/, ,/(((((((((((((/*. */(((((((((((((/*. ,%%#((/((((((* ,/(((((/(#&@@( ,%%##%%##((((((/*. ,/((((/(#&@@@@@@( ,%%######%%##((/(((/*. .*/(((//(%@@@@@@@@@@@( ,%%####%#(%%#%%##((/((((((((//#&@@@@@@&@@@@@@@@( ,%%####%( /#%#%%%##(//(#@@@@@@@%, #@@@@@@@( ,%%####%( *#%###%@@@@@@( #@@@@@@@( ,%%####%( #%#%@@@@, #@@@@@@@( ,%%##%%%( #%#%@@@@, #@@@@@@@( ,%%%#* #%#%@@@@, *%@@@( ., ,/##*. #%#%@@@@, ./&@#* *` ,/#%#####%%#/, #%#%@@@@, ,/&@@@@@@@@@&\. `*#########%%%%###%@@@@@@@@@@@@@@@@@@&*´ `*%%###########%@@@@@@@@@@@@@@&*´ `*%%%######%@@@@@@@@@@&*´ `*#%%##%@@@@@&*´ `*%#%@&*´ ███╗ ███╗ ██████╗██████╗ ██╗ ██╗███╗ ██╗██╗████████╗██╗ ██╗ ████╗ ████║██╔════╝██╔══██╗ ██║ ██║████╗ ██║██║╚══██╔══╝╚██╗ ██╔╝ ██╔████╔██║██║ ██████╔╝ ██║ ██║██╔██╗ ██║██║ ██║ ╚████╔╝ ██║╚██╔╝██║██║ ██╔═══╝ ██║ ██║██║╚██╗██║██║ ██║ ╚██╔╝ ██║ ╚═╝ ██║╚██████╗██║ ╚██████╔╝██║ ╚████║██║ ██║ ██║ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═╝

MCP Unity is an implementation of the Model Context Protocol for Unity Editor, allowing AI assistants to interact with your Unity projects. This package provides a bridge between Unity and a Node.js server that implements the MCP protocol, enabling AI agents like Claude, Windsurf, and Cursor to execute operations within the Unity Editor.

Features

MCP Unity currently provides the following tools:

  • execute_menu_item: Executes Unity menu items (functions tagged with the MenuItem attribute)
  • select_object: Selects game objects in the Unity hierarchy
  • package_manager: Installs, removes, and updates packages in the Unity Package Manager
  • run_tests: Runs tests using the Unity Test Runner
  • notify_message: Displays messages in the Unity Editor

MCP Unity currently provides the following resources:

  • get_menu_items: Retrieves a list of all available menu items in the Unity Editor to facilitate execute_menu_item tool
  • get_hierarchy: Retrieves a list of all game objects in the Unity hierarchy
  • get_console_logs: Retrieves a list of all logs from the Unity console
  • get_packages: Retrieves information about installed and available packages from the Unity Package Manager
  • get_assets: Retrieves information about assets in the Unity Asset Database
  • get_tests: Retrieves information about tests in the Unity Test Runner

Requirements

Installation

Installing this MCP Unity Server is a multi-step process:

Step 1: Install Unity MCP Server package via Unity Package Manager

  1. Open the Unity Package Manager (Window > Package Manager)
  2. Click the "+" button in the top-left corner
  3. Select "Add package from git URL..."
  4. Enter: https://github.com/CoderGamester/mcp-unity.git
  5. Click "Add"

Step 2: Install Node.js

To run MCP Unity server, you'll need to have Node.js 18 or later installed on your computer:

  1. Visit the Node.js download page
  2. Download the Windows Installer (.msi) for the LTS version (recommended)
  3. Run the installer and follow the installation wizard
  4. Verify the installation by opening PowerShell and running:
    node --version npm --version
  1. Visit the Node.js download page
  2. Download the macOS Installer (.pkg) for the LTS version (recommended)
  3. Run the installer and follow the installation wizard
  4. Alternatively, if you have Homebrew installed, you can run:
    brew install node@18
  5. Verify the installation by opening Terminal and running:
    node --version npm --version

Step 3: Configure AI LLM Client

Replace ABSOLUTE/PATH/TO with the absolute path to your MCP Unity installation.

The right configuration can be accessed in the Unity Editor MCP Server window (Tools > MCP Unity > Server Window)

To install MCP Unity via Smithery:

Currently not available

Open the MCP configuration file of your AI client (e.g. claude_desktop_config.json in Claude Desktop) and copy the following text:

Replace ABSOLUTE/PATH/TO with the absolute path to your MCP Unity installation.

{ "mcpServers": { "mcp-unity": { "command": "node", "args": [ "ABSOLUTE/PATH/TO/mcp-unity/Server/build/index.js" ], "env": { "UNITY_PORT": "8090" } } } }

Start Unity Editor MCP Server

  1. Open the Unity Editor
  2. Navigate to Tools > MCP Unity > Server Window
  3. Click "Start Server" to start the WebSocket server
  4. Open Claude Desktop or your AI Coding IDE (e.g. Cursor IDE, Windsurf IDE, etc.) and start executing Unity tools

Configure the WebSocket Port

By default, the WebSocket server runs on port 8080. You can change this port in two ways:

  1. Open the Unity Editor
  2. Navigate to Tools > MCP Unity > Server Window
  3. Change the "WebSocket Port" value to your desired port number
  4. Unity will setup the system environment variable UNITY_PORT to the new port number
  5. Restart the Node.js server
  6. Click again on "Start Server" to reconnect the Unity Editor web socket to the Node.js MCP Server
  1. Set the UNITY_PORT environment variable in the terminal
    • Powershell
    $env:UNITY_PORT = "8090"
    • Command Prompt/Terminal
    set UNITY_PORT=8090
  2. Restart the Node.js server
  3. Click again on "Start Server" to reconnect the Unity Editor web socket to the Node.js MCP Server

Debugging the Server

The MCP Unity server is built using Node.js . It requires to compile the TypeScript code to JavaScript in the build directory. To build the server, open a terminal and:

  1. Navigate to the Server directory:
    cd ABSOLUTE/PATH/TO/mcp-unity/Server
  2. Install dependencies:
    npm install
  3. Build the server:
    npm run build
  4. Run the server:
    node build/index.js

Debug the server with @modelcontextprotocol/inspector:

  • Powershell
$env:UNITY_PORT=8090; npx @modelcontextprotocol/inspector node Server/build/index.js
  • Command Prompt/Terminal
set UNITY_PORT=8090 && npx @modelcontextprotocol/inspector node Server/build/index.js

Don't forget to shutdown the server with Ctrl + C before closing the terminal or debugging it with the MCP Inspector.

  1. Enable logging on your terminal or into a log.txt file:
    • Powershell
    $env:LOGGING = "true" $env:LOGGING_FILE = "true"
    • Command Prompt/Terminal
    set LOGGING=true set LOGGING_FILE=true

Troubleshooting

  • Ensure the WebSocket server is running (check the Server Window in Unity)
  • Check if there are any firewall restrictions blocking the connection
  • Make sure the port number is correct (default is 8080)
  • Change the port number in the Unity Editor MCP Server window. (Tools > MCP Unity > Server Window)
  • Check the Unity Console for error messages
  • Ensure Node.js is properly installed and accessible in your PATH
  • Verify that all dependencies are installed in the Server directory
  • Ensure the menu item path is correct (case-sensitive)
  • Check if the menu item requires confirmation
  • Verify that the menu item is available in the current context

Support & Feedback

If you have any questions or need support, please open an issue on this repository.

Alternative you can reach out on

Contributing

Contributions are welcome! Please feel free to submit a Pull Request or open an Issue with your request.

Commit your changes following the Conventional Commits format.

License

This project is under MIT License

You must be authenticated.

A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

An implementation of the Model Context Protocol for Unity Editor, allowing AI assistants to interact with Unity projects through tools for executing menu items, selecting objects, managing packages, running tests, and accessing resources.

  1. Features
    1. Requirements
      1. <a name="install-server"></a>Installation
        1. Step 1: Install Unity MCP Server package via Unity Package Manager
        2. Step 2: Install Node.js
        3. Step 3: Configure AI LLM Client
      2. <a name="start-server"></a>Start Unity Editor MCP Server
        1. Configure the WebSocket Port
          1. <a name="debug-server"></a>Debugging the Server
            1. Troubleshooting
              1. Support & Feedback
                1. Contributing
                  1. License