Unity MCP Server
Integrates AI assistants with the Unity Editor for scene manipulation, asset management, and testing, plus Unity documentation search via RAG.
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
- Install the MCP Unity package in your Unity project
- Open
Tools > MCP Unity > Server Window - Click "Start Server" (default port: 8090)
- 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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。