|
|
||
|---|---|---|
| .. | ||
| registry | ||
| resources | ||
| tests | ||
| tools | ||
| Dockerfile | ||
| README.md | ||
| __init__.py | ||
| config.py | ||
| models.py | ||
| module_discovery.py | ||
| port_discovery.py | ||
| pyproject.toml | ||
| pyrightconfig.json | ||
| reload_sentinel.py | ||
| server.py | ||
| server_version.txt | ||
| telemetry.py | ||
| telemetry_decorator.py | ||
| test_telemetry.py | ||
| unity_connection.py | ||
| unity_instance_middleware.py | ||
| uv.lock | ||
README.md
MCP for Unity Server
Model Context Protocol server for Unity Editor integration. Control Unity through natural language using AI assistants like Claude, Cursor, and more.
Maintained by Coplay - This project is not affiliated with Unity Technologies.
💬 Join our community: Discord Server
Required: Install the Unity MCP Plugin to connect Unity Editor with this MCP server.
Installation
Option 1: Using uvx (Recommended)
Run directly from GitHub without installation:
uvx --from git+https://github.com/CoplayDev/unity-mcp@v6.3.0#subdirectory=Server mcp-for-unity
MCP Client Configuration:
{
"mcpServers": {
"UnityMCP": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/CoplayDev/unity-mcp@v6.3.0#subdirectory=Server",
"mcp-for-unity"
]
}
}
}
Option 2: Using uv (Local Installation)
For local development or custom installations:
# Clone the repository
git clone https://github.com/CoplayDev/unity-mcp.git
cd unity-mcp/Server
# Run with uv
uv run server.py
MCP Client Configuration:
Windows:
{
"mcpServers": {
"UnityMCP": {
"command": "uv",
"args": [
"run",
"--directory",
"C:\\path\\to\\unity-mcp\\Server",
"server.py"
]
}
}
}
macOS/Linux:
{
"mcpServers": {
"UnityMCP": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/unity-mcp/Server",
"server.py"
]
}
}
}
Option 3: Using Docker
docker build -t unity-mcp-server .
docker run unity-mcp-server
MCP Client Configuration:
{
"mcpServers": {
"UnityMCP": {
"command": "docker",
"args": ["run", "-i", "unity-mcp-server"]
}
}
}
Configuration
The server connects to Unity Editor automatically when both are running. No additional configuration needed.
Environment Variables:
DISABLE_TELEMETRY=true- Opt out of anonymous usage analyticsLOG_LEVEL=DEBUG- Enable detailed logging (default: INFO)
Example Prompts
Once connected, try these commands in your AI assistant:
- "Create a 3D player controller with WASD movement"
- "Add a rotating cube to the scene with a red material"
- "Create a simple platformer level with obstacles"
- "Generate a shader that creates a holographic effect"
- "List all GameObjects in the current scene"
Documentation
For complete documentation, troubleshooting, and advanced usage:
Requirements
- Python: 3.11 or newer
- Unity Editor: 2021.3 LTS or newer
- uv: Python package manager (Installation Guide)
License
MIT License - See LICENSE