quazaai/UnityMCPIntegration

This package provides a seamless integration between Model Context Protocol (MCP) and Unity Editor, allowing AI assistants to understand and interact with your Unity projects in real-time. With this integration, AI assistants can access information about your scene hierarchy, project settings, and execute code directly in the Unity Editor context.
📚 Features
- Browse and manipulate project files directly
- Access real-time information about your Unity project
- Understand your scene hierarchy and game objects
- Execute C# code directly in the Unity Editor
- Monitor logs and errors
- Control the Editor's play mode
- Wait For Code Execution
🚀 Getting Started
Prerequisites
- Unity 2021.3 or later
- Node.js 18+ (for running the MCP server)
Installation
1. Install Unity Package
You have several options to install the Unity package:
**Option A: Package Manager (Git URL)**
1. Open the Unity Package Manager (Window > Package Manager)
2. Click the + button and select Add package from git URL...
3. Enter the repository URL: https://github.com/quazaai/UnityMCPIntegration.git
4. Click Add
**Option B: Import Custom Package**
1. Clone this repository or download it as a unityPackage
2. In Unity, go to Assets > Import Package > Custom Package
3. Select the UnityMCPIntegration.unitypackage file
2. Set up the MCP Server
You have two options to run the MCP server:
**Option A: Run the server directly**
1. Navigate to the mcpServer (likely \Library\PackageCache\com.quaza.unitymcp@d2b8f1260bca\mcpServer\) directory
2. Install dependencies:
3. Run the server:
**Option B: Add to MCP Host configuration**
Add the server to your MCP Host configuration for Claude Desktop, Custom Implementation etc
Demo Video
Installing via Smithery
To install Unity MCP Integration for Claude Desktop automatically via Smithery:
🔧 Usage
Debugging and Monitoring
You can open the MCP Debug window in Unity to monitor the connection and test features:
1. Go to Window > MCP Debug
2. Use the debug window to:
- Check connection status
- Test code execution
- View logs
- Monitor events
Available Tools
The Unity MCP integration provides several tools to AI assistants:
Unity Editor Tools
- **get_editor_state**: Get comprehensive information about the Unity project and editor state
- **get_current_scene_info**: Get detailed information about the current scene
- **get_game_objects_info**: Get information about specific GameObjects in the scene
- **execute_editor_command**: Execute C# code directly in the Unity Editor
- **get_logs**: Retrieve and filter Unity console logs
- **verify_connection**: Check if there's an active connection to Unity Editor
Filesystem Tools
- **read_file**: Read contents of a file in your Unity project
- **read_multiple_files**: Read multiple files at once
- **write_file**: Create or overwrite a file with new content
- **edit_file**: Make targeted edits to existing files with diff preview
- **list_directory**: Get a listing of files and folders in a directory
- **directory_tree**: Get a hierarchical view of directories and files
- **search_files**: Find files matching a search pattern
- **get_file_info**: Get metadata about a specific file or directory