
Rubik's Cube MCP Server
Enables AI agents to solve Rubik's Cube puzzles through systematic manipulation with standard cube notation moves. Features real-time 3D visualization and interactive controls for tracking solving progress.
README
Rubik's Cube MCP Server
A Model Context Protocol (MCP) server that provides AI agents with the ability to solve Rubik's Cube puzzles through systematic manipulation and real-time visualization.
Features
- Interactive Cube Manipulation: Execute standard Rubik's Cube moves (U, D, L, R, F, B and their variations)
- 3D Real-time Visualization: Beautiful 3D cube visualization using Three.js and WebGL
- WebSocket Live Updates: Real-time state synchronization between MCP server and web interface
- Mouse Interaction: Rotate and examine the 3D cube with mouse controls
- Recursive Workflow: AI agents can systematically work through cube solving using nextAction guidance
- State Tracking: Complete move history and current cube state monitoring
- Solution Detection: Automatic detection when the cube is solved with celebration effects
Installation & Setup
Prerequisites
- Node.js 18.x or higher
- npm or yarn
Install Dependencies
cd rubiks-cube-mcp-server
npm install
Build the Project
npm run build
Run the Server
npx rubiks-cube-mcp-server
This will start both:
- MCP server on stdio (for AI agent communication)
- Web visualization server on
http://localhost:3000
Claude Desktop Configuration
To use this MCP server with Claude Desktop, add the following to your claude_desktop_config.json
:
{
"mcpServers": {
"rubiks-cube": {
"command": "npx",
"args": ["rubiks-cube-mcp-server"]
}
}
}
Configuration file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
After adding the configuration, restart Claude Desktop to load the MCP server.
MCP Tools
1. startCube
Initialize a new Rubik's Cube game session.
Parameters:
scramble
(optional, boolean): Whether to scramble the cube initially (default: true)
Returns:
- Game ID for the session
- Initial cube state
- Visualization URL
- Next action guidance
2. manipulateCube
Execute a move on the Rubik's Cube.
Parameters:
gameId
(string): The game session IDmove
(string): Standard cube notation (U, D, L, R, F, B, U', D', L', R', F', B', U2, D2, L2, R2, F2, B2)
Returns:
- Updated cube state
- Move execution confirmation
- Total moves count
- Next action guidance
3. finish
Complete the Rubik's Cube game session.
Parameters:
gameId
(string): The game session ID
Returns:
- Final game statistics
- Move history
- Completion status
Cube Notation
The server uses standard Rubik's Cube notation:
- U: Up face clockwise
- D: Down face clockwise
- L: Left face clockwise
- R: Right face clockwise
- F: Front face clockwise
- B: Back face clockwise
- ': Counter-clockwise (e.g., U')
- 2: Double turn (e.g., U2)
Example Usage with AI Agent
Agent: "Start a new Rubik's cube puzzle"
→ startCube tool called
→ Returns scrambled cube state and gameId
Agent: "Execute move U"
→ manipulateCube tool called with move "U"
→ Returns updated state and nextAction guidance
Agent: "Continue solving..."
→ Recursive manipulateCube calls until solved
→ finish tool called when complete
Web Visualization
Visit http://localhost:3000/game/{gameId}
to see:
- Real-time 3D cube representation
- Color-coded faces (White, Yellow, Red, Orange, Blue, Green)
- Move counter and history
- Interactive move buttons
- Solution status indicator
Architecture
- MCP Protocol: Standard Model Context Protocol for AI agent communication
- 3D Rendering: Three.js WebGL-based 3D cube visualization
- Real-time Communication: Socket.io WebSocket server for live updates
- Web Server: Express.js server for HTTP API and static content
- State Management: In-memory game session tracking with live synchronization
Workflow Pattern
The server follows the recursive MCP pattern:
- Start → Returns nextAction: 'manipulateCube'
- Manipulate → Returns nextAction: 'manipulateCube' (if not solved) or 'finish' (if solved)
- Finish → Returns nextAction: null (workflow complete)
This allows AI agents to work autonomously through the solving process.
Development
Watch Mode
npm run dev
Building
npm run build
Project Structure
src/
├── app.ts # Main MCP server setup
├── cubeLogic.ts # Rubik's Cube simulation logic
├── visualizationServer.ts # Web visualization server
└── types.ts # TypeScript interfaces
License
MIT License - see LICENSE file for details.
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。