Unity MCP Server

Unity MCP Server

Integrates AI assistants with the Unity Editor for scene manipulation, asset management, and testing, plus Unity documentation search via RAG.

Category
访问服务器

README

Unity MCP Server

A unified Model Context Protocol (MCP) server that combines Unity Editor integration and Unity knowledge base search capabilities for AI assistants.

Features

Unity Editor Integration (21 Tools)

Tool Description
execute_menu_item Execute Unity menu items by path
select_gameobject Select GameObjects in the editor
get_gameobject Get detailed GameObject information
update_gameobject Update or create GameObjects
delete_gameobject Delete GameObjects from the scene
duplicate_gameobject Duplicate GameObjects
find_gameobjects Search for GameObjects by name/tag/layer/component
update_component Add or modify components on GameObjects
add_asset_to_scene Instantiate prefabs/assets in the scene
create_prefab Create prefabs from GameObjects
create_scene Create new scenes
delete_scene Delete scenes
load_scene Load scenes (single or additive)
add_package Add packages via Package Manager
manage_asset Move, copy, rename, delete assets
run_tests Run Unity Test Runner tests
send_console_log Send messages to Unity console
get_console_logs Retrieve Unity console logs
recompile_scripts Force script recompilation
play_mode Control play mode (enter/exit/pause/step)
editor_selection Get/set editor selection

Unity Knowledge Search (1 Tool)

Tool Description
search_unity_knowledge Search Unity API docs, manual, and local assets via RAG

Resources (7)

Resource URI Description
Scene Hierarchy unity://scenes_hierarchy All GameObjects in loaded scenes
GameObject unity://gameobject/{id} Detailed GameObject info
Menu Items unity://menu-items Available Unity menu items
Console Logs unity://logs/{type} Console logs with filtering
Packages unity://packages Package Manager packages
Assets unity://assets Asset Database contents
Tests unity://tests/{mode} Test Runner tests

Installation

npm install
npm run build

Usage

Basic Configuration

Add to your MCP configuration (e.g., .mcp.json):

{
  "mcpServers": {
    "unity-mcp": {
      "command": "node",
      "args": ["path/to/unity-mcp/build/index.js"],
      "env": {
        "UNITY_PORT": "8090"
      }
    }
  }
}

With RAG Knowledge Search

To enable Unity documentation search, configure the RAG server:

{
  "mcpServers": {
    "unity-mcp": {
      "command": "node",
      "args": ["path/to/unity-mcp/build/index.js"],
      "env": {
        "UNITY_PORT": "8090",
        "RAG_PYTHON_PATH": "python",
        "RAG_SERVER_PATH": "path/to/unity-rag-server",
        "RAG_DB_PATH": "path/to/unity-rag-server/data"
      }
    }
  }
}

Environment Variables

Variable Description Default
UNITY_PORT Unity WebSocket server port 8090
UNITY_HOST Unity WebSocket server host localhost
LOGGING Enable console logging false
LOGGING_FILE Enable file logging false
RAG_PYTHON_PATH Path to Python executable -
RAG_SERVER_PATH Path to RAG server directory -
RAG_DB_PATH Path to RAG database -

Unity Editor Setup

  1. Install the MCP Unity package in your Unity project
  2. Open Tools > MCP Unity > Server Window
  3. Click "Start Server" (default port: 8090)
  4. The MCP server will connect automatically

Architecture

+-------------------+     STDIO      +-------------------+
|   AI Assistant    | <-----------> |   Unity MCP       |
|   (Claude, etc)   |               |   Server (Node)   |
+-------------------+               +--------+----------+
                                             |
                            WebSocket (8090) |
                                             v
                                    +--------+----------+
                                    |   Unity Editor    |
                                    |   (C# Plugin)     |
                                    +-------------------+

Development

# Build
npm run build

# Watch mode
npm run watch

# Run with MCP Inspector
npm run inspector

# Start
npm start

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选