unity-mcp

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks w

What is unity-mcp?

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

Overview of unity-mcp

What it is

Unity MCP is an open-source bridge between AI assistants (such as Claude, Codex, VS Code, local LLMs, and others) and the Unity Editor. It uses the Model Context Protocol (MCP) to give large language models tools to manage assets, control scenes, edit scripts, run tests, and automate game development workflows within Unity.

Key features

50 focused MCP tool entrypoints for controlling the Unity Editor from any MCP client
Create scenes and GameObjects, edit C# scripts, manage assets, run tests, profile, and build
Supports Unity 2021.3 LTS through 6.x, Python 3.10+ (via uv)
Works with any MCP client: Claude Desktop & Code, Cursor, VS Code, Windsurf, Cline, Gemini CLI, and more
Multi-Instance Routing for multiple Unity instances
Tool groups (vfx, animation, ui, testing, etc.) with Roslyn script validation and remote server auth

Use cases

Game developers and technical artists can use Unity MCP to automate repetitive tasks in Unity, such as creating GameObjects, editing scripts, managing assets, and running tests through natural language prompts. It is also useful for rapid prototyping, AI-assisted scene building, and integrating LLM-based workflows into existing Unity pipelines.

Getting started

1. Install in Unity: Package Manager → Add from git URL: https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main (pin #v10.0.0 for this release, or: openupm add com.coplaydev.unity-mcp)2. Configure: Window → MCP for Unity → Configure All Detected Clients.3. Prompt the AI assistant, e.g., 'Create a cube at the origin and add a Rigidbody.'

License and pricing

This project is licensed under the MIT License. It is open-source and free to use.

這是什麼

Unity MCP 是一個開放原始碼的橋樑，可連接 AI 輔助工具（例如 Claude、Codex、VS Code、本地 LLM 等）與 Unity Editor。它透過模型上下文協定 (MCP) 讓大型語言模型擁有管理資源、控制場景、編輯腳本、執行測試以及自動化 Unity 遊戲開發工作流程的能力。

主要功能

50 個專注的 MCP 工具進入點，可從任何 MCP 客戶端控制 Unity Editor
建立場景與遊戲物件、編輯 C# 腳本、管理資源、執行測試、效能分析以及建置
支援 Unity 2021.3 LTS 至 6.x、Python 3.10+（透過 uv）
可與任何 MCP 客戶端搭配使用：Claude Desktop & Code、Cursor、VS Code、Windsurf、Cline、Gemini CLI 等
多執行個體路由，支援多個 Unity 實例
工具群組（VFX、動畫、UI、測試等），包含 Roslyn 腳本驗證與遠端伺服器驗證

使用情境

遊戲開發者與技術美術人員可以使用 Unity MCP，透過自然語言提示自動化 Unity 中的重複性任務，例如建立遊戲物件、編輯腳本、管理資源以及執行測試。它也適用於快速原型製作、AI 輔助場景建置，以及將基於 LLM 的工作流程整合到現有的 Unity 管線中。

快速開始

1. 在 Unity 中安裝：套件管理器 → 從 Git URL 加入： https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main (固定 #v10.0.0 版本，或執行：openupm add com.coplaydev.unity-mcp)2. 設定：視窗 → MCP for Unity → 設定所有已偵測的客戶端。3. 對 AI 輔助工具下達提示，例如「在原點建立一個立方體並加入 Rigidbody」。

授權與價格

本專案採用 MIT 授權條款，為開放原始碼且免費使用。

Based on the project's public README and repository metadata.