BlockbenchMCP

BlockbenchMCP

Connects Claude AI to Blockbench through Model Context Protocol, enabling AI-assisted 3D modeling, texture creation, and block model manipulation with real-time command execution and feedback.

Category
访问服务器

README

BlockbenchMCP - Blockbench Model Context Protocol Integration

BlockbenchMCP connects Blockbench to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blockbench. This integration enables AI-assisted 3D modeling, texture creation, and block model manipulation.

🚀 Features

  • Two-way communication: Connect Claude AI to Blockbench through a socket-based server
  • Real-time command tracking: Monitor all MCP commands with a dedicated history panel
  • Model manipulation: Create, modify, and delete block models in Blockbench
  • Live feedback: Get instant responses from Blockbench operations
  • Extensible architecture: Easy to add new tools and capabilities

🏗️ Components

The system consists of two main components:

  1. Blockbench Plugin (apps/mcp-plugin): A Blockbench plugin that creates a socket server within Blockbench to receive and execute commands
  2. MCP Server (apps/mcp-server): A Node.js server that implements the Model Context Protocol and connects to the Blockbench plugin

📦 Project Structure

blockbench-mcp/
├── apps/
│   ├── mcp-server/      # MCP server implementation
│   └── mcp-plugin/      # Blockbench plugin
└── packages/
    └── shared/          # Shared TypeScript types

�️ Installation

Prerequisites

  • Blockbench 4.0 or newer
  • Node.js 18.0 or newer
  • pnpm package manager

Install pnpm if you haven't already:

npm install -g pnpm

1. Clone and Setup

git clone https://github.com/enfpdev/blockbench-mcp.git
cd blockbench-mcp
pnpm install

2. Build the Project

pnpm build

3. Install the Blockbench Plugin

  1. Build the plugin: cd apps/mcp-plugin && pnpm build
  2. Open Blockbench
  3. Go to File > Plugins > Load Plugin from File
  4. Select the built plugin file from apps/mcp-plugin/dist/
  5. Enable the plugin by checking the box next to "MCP Plugin"

4. Claude Desktop Integration

Add the following to your Claude Desktop configuration file:

Location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Configuration:

{
  "mcpServers": {
    "blockbench": {
      "command": "node",
      "args": [
        "/path/to/blockbench-mcp/apps/mcp-server/dist/index.js"
      ]
    }
  }
}

🎮 Usage

Starting the Connection

  1. In Blockbench, open the plugin panel (if not visible, go to View > Panels)
  2. Find the "MCP Plugin" panel
  3. Click "Connect to MCP Server"
  4. The plugin will start listening on port 9999

Using with Claude

Once the configuration is set in Claude Desktop and the plugin is running in Blockbench, you'll see a hammer icon with tools for Blockbench MCP.

Capabilities

  • Get model and project information
  • Create, delete, and modify block models
  • Apply textures and materials
  • Execute custom modeling operations
  • Real-time command history tracking

Example Commands

Here are some examples of what you can ask Claude to do:

  • "Create a simple sword model with proper proportions"
  • "Add a crossguard to the existing sword model"
  • "Create a chest model with opening animation"
  • "Generate a pickaxe tool with different material variants"
  • "Show me the current model structure and elements"
  • "Create a character head with facial features"

🔧 Development

Development Mode

# Start both server and plugin in development mode
pnpm dev

# Or start individually
cd apps/mcp-server && pnpm dev
cd apps/mcp-plugin && pnpm dev

Version Management

This project uses Changesets for version management:

# Record changes
pnpm changeset

# Update versions
pnpm version

# Build all packages
pnpm build

🐛 Troubleshooting

  • Connection issues: Make sure the Blockbench plugin is running and the MCP server is configured in Claude Desktop
  • Port conflicts: The plugin uses port 9999 by default. Make sure no other application is using this port
  • Plugin not loading: Verify that the plugin file is properly built and Blockbench version is compatible
  • Command timeouts: Try simplifying your requests or breaking them into smaller steps

🔧 Technical Details

Communication Protocol

The system uses Socket.IO for real-time communication between components:

  • WebSocket connection on port 9999
  • JSON-based commands with type and payload structure
  • Event-driven architecture for responsive interactions

Architecture

Claude AI ← MCP Protocol → MCP Server ← Socket.IO → Blockbench Plugin

⚠️ Limitations & Security Considerations

  • The plugin allows executing code within Blockbench, which can be powerful but potentially risky
  • Always save your work before using experimental features
  • Complex operations might need to be broken down into smaller steps
  • Network communication happens over localhost only for security

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

� License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments


Disclaimer: This is a third-party integration and not officially affiliated with Blockbench.

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