Unity AI MCP Server

A Model Context Protocol (MCP) server for Unity AI integration with Smithery.ai support.

Features

- MCP server for Unity AI integration
- RESTful API for tool access
- Stdin/Stdout interface for direct communication
- Unity project analysis tools
- Script generation and manipulation
- Sandbox mode for safe execution
- Smithery.ai integration for advanced AI capabilities

Installation

1. Clone this repository:

git clone https://github.com/GrandMasterK414/unity-ai-mcp-server-new.git

cd unity-ai-mcp-server-new

2. Install dependencies:

npm install

3. Copy the example environment file and configure it:

cp .env.example .env

4. Edit the .env file to set your Unity project path and other configurations.

5. Build the project:

npm run build

Usage

Start the Server

npm start

Development Mode

npm run dev

Configuration

Edit the .env file to configure the server:

- UNITY_PROJECT_PATH: Path to your Unity project (required)
- UNITY_EDITOR_PATH: Path to Unity Editor executable (required for sandbox mode)
- PORT: Server port (default: 3000)
- HOST: Server host (default: localhost)
- LOG_LEVEL: Logging level (error, warn, info, debug)
- ENABLE_SANDBOX: Enable sandbox mode (0 or 1)
- ENABLE_REST_API: Enable REST API (0 or 1)
- ENABLE_STDIN_INTERFACE: Enable stdin interface (0 or 1)
- ENABLE_CORS: Enable CORS for REST API (0 or 1)

See the .env.example file for all available configuration options.

Smithery.ai Integration

This server includes integration with Smithery.ai's advanced AI tools. To enable and configure the Smithery.ai integration:

1. Set SMITHERY_ENABLED=1 in your .env file
2. Add your Smithery.ai API key as SMITHERY_API_KEY in your .env file

For detailed information about the Smithery.ai integration, see the Smithery Integration Documentation.

Available Tools

- Project Explorer: Navigate and explore Unity project structure
- Script Advisor: Get guidance on Unity script development
- Asset Reference Finder: Find references to assets in your project
- Sandbox Runner: Safely execute code in a Unity Editor instance
- Smithery.ai Tools: Access Smithery.ai's AI capabilities

API Documentation

For detailed API documentation, see the API Documentation.

Contributing

For contribution guidelines, see CONTRIBUTING.md.

License

This project is licensed under the MIT License. See the LICENSE file for details.