Unity AI Bridge

🚀 Unity-MCP

Unity-MCP is a bridge project that connects the Unity engine with AI assistants. It enables communication and interaction between AI assistants and Unity applications through the JSON-RPC protocol.

🚀 Quick Start

Unity-MCP serves as a crucial link, facilitating seamless communication between AI assistants and Unity applications via the JSON - RPC protocol.

✨ Features

• Direct code execution: Supports direct execution of code snippets in the Unity runtime environment.
• Read - only access: Provides a read - only access interface to the Unity object model.
• Scalable architecture: Features a scalable architecture design, making it easy to add more functional modules.
• Robust error handling: Comes with a powerful error - handling mechanism.
• Unified logging: Offers unified logging and tracking capabilities.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

Execute Code

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "execute_code", 
    "arguments": {
      "code": "Debug.Log(\"Hello from Unity!\"); return GameObject.FindObjectsOfType<GameObject>().Length;",
      "timeout": 5000
    }
  }
}

Query Object

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call", 
  "params": {
    "name": "query",
    "arguments": {
      "query": "Camera.main.transform.position",
      "timeout": 5000
    }
  }
}

Get Log

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call", 
  "params": {
    "name": "get_log_by_name",
    "arguments": {
      "log_name": "unity-execute-1712534400000",
      "limit": 1
    }
  }
}

Advanced Usage

Once the AI assistant gains access to the Unity tools, it can perform the following operations:

Can you execute the following C# code in this Unity project?

GameObject.Find("Player").transform.position = new Vector3(0, 1, 0);

📚 Documentation

Core Architecture

• JSON - RPC Interface: The project is designed based on the JSON - RPC 2.0 specification, offering a series of RPC methods for interacting with the Unity engine.
• Toolset: Provides multiple functional modules:
  • execute_code: Executes arbitrary C# code in the Unity runtime environment.
  • query: Queries Unity objects, properties, and methods using dot notation.
  • get_log_by_name: Retrieves specific log entries from the AILogger.
• Asynchronous Execution: All operations support asynchronous execution, ensuring high performance and a responsive experience.

📄 License

This project is licensed under the MIT license.

👨‍💻 Author

T Savo (@TSavo)