yunuscan

MCP For Unity

by yunuscan

開発ツール

Enables AI clients to interact with and control the Unity Editor through a Python MCP server bridge, allowing natural language-based Unity project manipulation.

GitHubで見る

MCP For Unity

This project implements a Model Context Protocol (MCP) server that acts as a bridge to the Unity Editor.

Structure

Server/: Contains the Python MCP server that AI clients connect to.
Scripts/: Contains the Unity C# scripts.
package.json: Unity Package definition file.

Installation

1. Unity Setup (via Package Manager)

You can install the Unity integration directly from GitHub using the Unity Package Manager.

Open Unity.
Go to Window > Package Manager.
Click the + button in the top-left corner.
Select Add package from git URL....

Enter the following URL:

https://github.com/yunuscan/MCPForUnity.git

Click Add.

2. Python Server Setup (via Unity Editor)

In Unity, go to UnityMCP > Dashboard.
Click Install 'uv' and Requirements.
Click Start Python MCP Server (uv run) to test the connection.

3. Client Configuration (VS Code / Copilot / Claude)

To use this with your AI assistant:

Open the UnityMCP > Dashboard window.
Click Configure for VS Code (Copilot).
- This will generate a .vscode/mcp.json file in your project root.
- It will also create a tasks.json to easily run the server.
Alternatively, copy the JSON config manually for Claude Desktop or Cursor.

Usage

Ensure the Unity project is open.
Connect your AI client using the generated configuration.
Ask your AI to "Create a cube" or "Check console logs".