Unity MCP server

Unity MCP is a bridge between Large Language Models (LLMs) and Unity, allowing AI to understand and interact with Unity's tools through a dedicated server. It enables LLMs to manipulate GameObjects, work with assets, modify components, and control various aspects of the Unity Editor based on user requests.

Installation

To set up the Unity MCP server and plugin:

1. Install prerequisites:

   • .NET 9.0
   • OpenUPM-CLI

2. Add the package to your Unity project:

   openupm add com.ivanmurzak.unity.mcp
   

Using Unity MCP

Initial Setup

1. Ensure your project path doesn't contain spaces:

   • ✅ C:/MyProjects/Project
   • ❌ C:/My Projects/Project

2. Open the AI Connector window in Unity:

   • Navigate to Window/AI Connector (Unity-MCP)

3. Install an MCP client:

   • Cursor (recommended)
   • Claude Desktop

Connecting to an LLM

1. Sign in to your MCP client
2. Click the Configure button in your MCP client
3. Restart your MCP client
4. Verify that the "AI Connector" status shows "Connected" or "Connecting..."
5. Test the connection by typing a question in your client chat, such as:

   Explain my scene hierarchy
   

Creating Custom Tools

You can extend Unity MCP with your own custom tools:

[McpPluginToolType]
public class Tool_GameObject
{
    [McpPluginTool
    (
        "MyCustomTask",
        Title = "Create a new GameObject"
    )]
    [Description("Explain here to LLM what is this, when it should be called.")]
    public string CustomTask
    (
        [Description("Explain to LLM what is this.")]
        string inputData
    )
    {
        // do anything in background thread

        return MainThread.Run(() =>
        {
            // do something in main thread if needed

            return $"[Success] Operation completed.";
        });
    }
}

Requirements for Custom Tools

1. Create a class with the McpPluginToolType attribute
2. Add methods with the McpPluginTool attribute
3. Optional: Add Description attributes to method arguments to help the LLM understand them
4. Optional: Use nullable parameters with default values to mark them as optional for the LLM

Note: Use MainThread.Run(() => { }) when you need to interact with the Unity API, which requires execution on the main thread.

Available AI Tools

Unity MCP includes tools for:

• GameObjects: Create, destroy, find, modify, set parent, duplicate
• Components: Add, get, modify, destroy
• Editor: Control playmode, manage windows, work with layers and tags
• Selection: Get and set selection
• Prefabs: Instantiate, open, modify, save, close
• Assets: Create, find, refresh, read, modify, rename, delete, move
• Scenes: Create, save, load, unload, get hierarchy
• Materials: Create, modify, read, assign
• Shaders: List all
• Scripts: Read, update, create, delete

Many more features are planned for future updates.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.