Model Context Protocol (MCP) Server for Unity
About
# Model Context Protocol (MCP) Server for Unity A Unity package that connects Unity with AI assistants (Claude, Cursor AI, and Windsurf) through the Model Context Protocol. ## Features - Connect Unity with multiple AI services: - Claude AI - Cursor AI - Windsurf - Enable AI services to access: - Unity Console (errors…
Details
- License
- MIT license
Explore
- Connect Unity with multiple AI services:
- Claude AI
- Cursor AI
- Windsurf
- Enable AI services to access:
- Unity Console (errors, warnings, logs)
- Project Browser (assets)
- Scene Hierarchy (GameObjects)
- Inspector (properties)
1. Open the MCP Server window (Window > MCP > Server)
2. Configure your AI service credentials
3. Start the server
4. Connect your AI assistant to the provided endpoint
1. Clone this repository
2. Copy the contents to your Unity project's Packages folder
A Unity package that connects Unity with AI assistants (Claude, Cursor AI, and Windsurf) through the Model Context Protocol.
Features
- Connect Unity with multiple AI services:
- Claude AI
- Cursor AI
- Windsurf
- Enable AI services to access:
- Unity Console (errors, warnings, logs)
- Project Browser (assets)
- Scene Hierarchy (GameObjects)
- Inspector (properties)
Installation
Using Git URL
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 the following URL: https://github.com/folkward99/mcp-server.git
5. Click "Add"
Manual Installation
1. Clone this repository
2. Copy the contents to your Unity project's Packages folder
Usage
1. Open the MCP Server window (Window > MCP > Server)
2. Configure your AI service credentials
3. Start the server
4. Connect your AI assistant to the provided endpoint
Configuration
API Keys
To use the MCP Server, you'll need API keys for the AI services you want to connect:
- Claude AI: Get API Key
- Cursor AI: Get API Key
- Windsurf: Get API Key
Server Settings
- Port: The port number for the MCP server (default: 8080)
- Update Frequency: How often to send updates to AI services (in seconds)
- Log Level: Detail level for server logs
Documentation
For detailed documentation, see the Documentation folder.
Examples
Check out the example scenes in the Samples~/Examples folder to see the MCP Server in action.
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



