iflow-mcp_unity-mcp 8.1.4

MCP for Unity Server: A Unity package for Unity Editor integration via the Model Context Protocol (MCP).

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:

# HTTP (default)
uvx --from git+https://github.com/CoplayDev/unity-mcp@v8.1.4#subdirectory=Server \
    mcp-for-unity --transport http --http-url http://localhost:8080

# Stdio
uvx --from git+https://github.com/CoplayDev/unity-mcp@v8.1.4#subdirectory=Server \
    mcp-for-unity --transport stdio

MCP Client Configuration (HTTP):

{
  "mcpServers": {
    "UnityMCP": {
      "url": "http://localhost:8080/mcp"
    }
  }
}

MCP Client Configuration (stdio):

{
  "mcpServers": {
    "UnityMCP": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/CoplayDev/unity-mcp@v8.1.4#subdirectory=Server",
        "mcp-for-unity",
        "--transport",
        "stdio"
      ],
      "type": "stdio"
    }
  }
}

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 (HTTP)
uv run server.py --transport http --http-url http://localhost:8080

# Run with uv (stdio)
uv run server.py --transport stdio

MCP Client Configuration (HTTP):

{
  "mcpServers": {
    "UnityMCP": {
      "url": "http://localhost:8080/mcp"
    }
  }
}

MCP Client Configuration (stdio – Windows):

{
  "mcpServers": {
    "UnityMCP": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "C:\\path\\to\\unity-mcp\\Server",
        "server.py",
        "--transport",
        "stdio"
      ]
    }
  }
}

MCP Client Configuration (stdio – macOS/Linux):

{
  "mcpServers": {
    "UnityMCP": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/unity-mcp/Server",
        "server.py",
        "--transport",
        "stdio"
      ]
    }
  }
}

Option 3: Using Docker

docker build -t unity-mcp-server .
docker run -p 8080:8080 unity-mcp-server --transport http --http-url http://0.0.0.0:8080

Configure your MCP client with "url": "http://localhost:8080/mcp". For stdio-in-docker (rare), run the container with --transport stdio and use the same command/args pattern as the uv examples, wrapping it in docker run -i ... if needed.

---

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 analytics
• LOG_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:

📖 Full Documentation

---

Requirements

• Python: 3.10 or newer
• Unity Editor: 2021.3 LTS or newer
• uv: Python package manager (Installation Guide)

---

License

MIT License - See LICENSE