Unity Editor MCP Server

Integrations

  • Allows AI assistants to interact with Unity projects, providing tools to execute menu items and perform operations within the Unity Editor.

MCP Unity Editor (Game Engine)

English🇨🇳简体中文🇯🇵日本語
,/(/. *(/, */(((((/. *((((((*. .*((((((((((/. *((((((((((/. ./((((((((((((((/ *((((((((((((((/, ,/(((((((((((((/*. */(((((((((((((/*. ,%%#((/((((((* ,/(((((/(#&@@( ,%%##%%##((((((/*. ,/((((/(#&@@@@@@( ,%%######%%##((/(((/*. .*/(((//(%@@@@@@@@@@@( ,%%####%#(%%#%%##((/((((((((//#&@@@@@@&@@@@@@@@( ,%%####%( /#%#%%%##(//(#@@@@@@@%, #@@@@@@@( ,%%####%( *#%###%@@@@@@( #@@@@@@@( ,%%####%( #%#%@@@@, #@@@@@@@( ,%%##%%%( #%#%@@@@, #@@@@@@@( ,%%%#* #%#%@@@@, *%@@@( ., ,/##*. #%#%@@@@, ./&@#* *` ,/#%#####%%#/, #%#%@@@@, ,/&@@@@@@@@@&\. `*#########%%%%###%@@@@@@@@@@@@@@@@@@&*´ `*%%###########%@@@@@@@@@@@@@@&*´ `*%%%######%@@@@@@@@@@&*´ `*#%%##%@@@@@&*´ `*%#%@&*´ ███╗ ███╗ ██████╗██████╗ ██╗ ██╗███╗ ██╗██╗████████╗██╗ ██╗ ████╗ ████║██╔════╝██╔══██╗ ██║ ██║████╗ ██║██║╚══██╔══╝╚██╗ ██╔╝ ██╔████╔██║██║ ██████╔╝ ██║ ██║██╔██╗ ██║██║ ██║ ╚████╔╝ ██║╚██╔╝██║██║ ██╔═══╝ ██║ ██║██║╚██╗██║██║ ██║ ╚██╔╝ ██║ ╚═╝ ██║╚██████╗██║ ╚██████╔╝██║ ╚████║██║ ██║ ██║ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═╝

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

IDE Integration - Package Cache Access

MCP Unity provides automatic integration with VSCode-like IDEs (Visual Studio Code, Cursor, Windsurf) by adding the Unity Library/PackedCache folder to your workspace. This feature:

  • Improves code intelligence for Unity packages
  • Enables better autocompletion and type information for Unity packages
  • Helps AI coding assistants understand your project's dependencies

MCP Server Tools

  • execute_menu_item: Executes Unity menu items (functions tagged with the MenuItem attribute)

    Example prompt: "Execute the menu item 'GameObject/Create Empty' to create a new empty GameObject"

  • select_gameobject: Selects game objects in the Unity hierarchy by path or instance ID

    Example prompt: "Select the Main Camera object in my scene"

  • update_component: Updates component fields on a GameObject or adds it to the GameObject if it does not contain the component

    Example prompt: "Add a Rigidbody component to the Player object and set its mass to 5"

  • add_package: Installs new packages in the Unity Package Manager

    Example prompt: "Add the TextMeshPro package to my project"

  • run_tests: Runs tests using the Unity Test Runner

    Example prompt: "Run all the EditMode tests in my project"

  • send_console_log: Send a console log to Unity

    Example prompt: "Send a console log to Unity Editor"

  • add_asset_to_scene: Adds an asset from the AssetDatabase to the Unity scene

    Example prompt: "Add the Player prefab from my project to the current scene"

MCP Server Resources

  • unity://menu-items: Retrieves a list of all available menu items in the Unity Editor to facilitate execute_menu_item tool

    Example prompt: "Show me all available menu items related to GameObject creation"

  • unity://hierarchy: Retrieves a list of all game objects in the Unity hierarchy

    Example prompt: "Show me the current scene hierarchy structure"

  • unity://gameobject/{id}: Retrieves detailed information about a specific GameObject by instance ID or object path in the scene hierarchy, including all GameObject components with it's serialized properties and fields

    Example prompt: "Get me detailed information about the Player GameObject"

  • unity://logs: Retrieves a list of all logs from the Unity console

    Example prompt: "Show me the recent error messages from the Unity console"

  • unity://packages: Retrieves information about installed and available packages from the Unity Package Manager

    Example prompt: "List all the packages currently installed in my Unity project"

  • unity://assets: Retrieves information about assets in the Unity Asset Database

    Example prompt: "Find all texture assets in my project"

  • unity://tests/{testMode}: Retrieves information about tests in the Unity Test Runner

    Example prompt: "List all available tests in my Unity project"

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
  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

Step 3: Configure AI LLM Client

  1. Open the Unity Editor
  2. Navigate to Tools > MCP Unity > Server Window
  3. Click on the "Configure" button for your AI LLM client as shown in the image below

  1. Confirm the configuration installation with the given popup

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 or just copy the text from the Unity Editor MCP Server window (Tools > MCP Unity > Server Window).

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

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

When the AI client connects to the WebSocket server, it will automatically show in the green box in the window

Optional: Set WebSocket Port

By default, the WebSocket server runs on port 8090. 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

Optional: Set Timeout

By default, the timeout between the MCP server and the WebSocket is 10 seconds. You can change depending on the OS you are using:

  1. Open the Unity Editor
  2. Navigate to Tools > MCP Unity > Server Window
  3. Change the "Request Timeout (seconds)" value to your desired timeout seconds
  4. Unity will setup the system environment variable UNITY_REQUEST_TIMEOUT to the new timeout value
  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

For non-Windows OS, you need to configure two places:

In Editor Process Timeout

  1. Open the Unity Editor
  2. Navigate to Tools > MCP Unity > Server Window
  3. Change the "Request Timeout (seconds)" value to your desired timeout seconds

WebSocket Timeout

  1. Set the UNITY_REQUEST_TIMEOUT environment variable in the terminal
    • Powershell
    $env:UNITY_REQUEST_TIMEOUT = "300"
    • Command Prompt/Terminal
    set UNITY_REQUEST_TIMEOUT=300
  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

Tip


The timeout between your AI Coding IDE (e.g., Claude Desktop, Cursor IDE, Windsurf IDE) and the MCP Server depends on the IDE.

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
npx @modelcontextprotocol/inspector node Server/build/index.js
  • Command Prompt/Terminal
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)
  • Send a console log message from MCP client to force a reconnection between MCP client and Unity server
  • 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

The run_tests tool returns the following response:

Error: Connection failed: Unknown error

This error occurs because the bridge connection is lost when the domain reloads upon switching to Play Mode.
The workaround is to turn off Reload Domain in Edit > Project Settings > Editor > "Enter Play Mode Settings".

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

Acknowledgements

Related MCP Servers

  • -
    security
    A
    license
    -
    quality
    Model Context Protocol (MCP) server implementation that enables Claude Desktop to interact with Google's Gemini AI models.
    Last updated -
    53
    TypeScript
    MIT License
    • Apple
    • Linux
  • A
    security
    A
    license
    A
    quality
    A tool that helps manage and synchronize MCP server configurations across different AI assistant clients (Cline, Roo Code, WindSurf, Claude), automating the process of retrieving, listing, adding, and removing server configurations from client configuration files.
    Last updated -
    6
    6
    1
    JavaScript
    MIT License
    • Apple
  • A
    security
    F
    license
    A
    quality
    A server built on mcp-framework that enables integration with Claude Desktop through the Model Context Protocol.
    Last updated -
    1
    • Apple
  • -
    security
    A
    license
    -
    quality
    An MCP server that enables other AI models (like Claude) to use Google's Gemini models as tools for specific tasks through a standardized interface.
    Last updated -
    1
    TypeScript
    MIT License

View all related MCP servers

ID: wajaojujfa