Chat with Blender

Chat with Blender

Enables AI assistants to control Blender 3D modeling and rendering through natural language commands via the Model Context Protocol.

Category
访问服务器

README

<div align="center"> <img src="assets/logo.png" alt="Chat with Blender Logo" width="200"> <h1>Chat with Blender</h1> <h3>Blender MCP Server</h3> </div>

<p align="center"> <img src="https://img.shields.io/badge/Blender-3.0%2B-orange?logo=blender" alt="Blender 3.0+"> <img src="https://img.shields.io/badge/Python-3.10%2B-blue?logo=python" alt="Python 3.10+"> <img src="https://img.shields.io/badge/MCP-Compatible-green" alt="MCP Compatible"> <img src="https://img.shields.io/badge/License-MIT-yellow" alt="MIT License"> <img src="https://img.shields.io/badge/Vibe-Coded-ff69b4" alt="Vibe Coded"> </p>

<p align="center"> <strong>🎨 Control Blender with AI</strong><br> Create, edit, and render 3D models through chat </p>

<p align="center"> <a href="#-features">Features</a> • <a href="#-installation">Installation</a> • <a href="#-usage">Usage</a> • <a href="#%EF%B8%8F-mcp-tools">MCP Tools</a> • <a href="#-security">Security</a> </p>


⚡ Vibe Coding Project: This project was developed with AI assistant help using the "vibe coding" approach. It may contain experimental features and unexpected bugs. Your contributions and bug reports are highly appreciated!


🎬 Demo

<p align="center"> <img src="screenshots/scene-example.png" alt="Chat with Blender Demo" width="800"> </p>

<p align="center"> <em>AI-generated terrarium scene - trees, clouds, and glass box</em> </p>


✨ Features

Chat with Blender enables AI assistants to directly control Blender using the Model Context Protocol (MCP).

Feature Description
🎯 Object Creation Cube, sphere, cylinder, torus, text, and more
🔧 Object Editing Modify position, rotation, scale
🎭 Material Control Color, metallic, roughness, emission settings
💡 Lighting Point, Sun, Spot, Area lights
📷 Camera Camera creation and setup
🖼️ Render Convert scene to image
🐍 Code Execution Execute custom Python code

Supported Platforms

<table> <tr> <td align="center"><img src="https://upload.wikimedia.org/wikipedia/commons/8/8a/Claude_AI_logo.svg" width="60"><br><strong>Claude Desktop</strong></td> <td align="center"><img src="https://lmstudio.ai/favicon.ico" width="60"><br><strong>LM Studio</strong></td> <td align="center"><img src="https://cursor.sh/favicon.ico" width="60"><br><strong>Cursor</strong></td> </tr> </table>


⚠️ Important Warnings

🧪 Experimental Project

This project is in active development. You may encounter:

  • 🐛 Unexpected bugs and crashes
  • 🔄 API changes
  • 📦 Missing features
  • 🎨 Material/color issues (check viewport mode!)

Our recommendation: Save and backup your important Blender projects!


🚀 Installation

Requirements

  • Blender 3.0 or higher (5.0+ tested)
  • Python 3.10 or higher
  • Claude Desktop or LM Studio (MCP supported)

Step 1: Download the Project

git clone https://github.com/Akerdogmus/chat-with-blender.git
cd chat-with-blender

Step 2: Install Python Dependencies

pip install mcp httpx

Step 3: Install the Blender Addon

  1. Open Blender
  2. Go to Edit → Preferences → Add-ons menu
  3. Click the "Install..." button in the top right
  4. Select the downloaded addon.py file
  5. Check the "Interface: Blender MCP" checkbox

<p align="center"> <img src="screenshots/chat-with-blender-kurulum.png" alt="Blender Addon Installation" width="600"> </p>

Step 4: MCP Client Configuration

For Claude Desktop

  1. Open the config file:

    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  2. Add the following configuration:

{
  "mcpServers": {
    "blender": {
      "command": "python",
      "args": ["C:/path/to/chat-with-blender/run_server.py"]
    }
  }
}

⚠️ Important: Replace C:/path/to/chat-with-blender/ with your own project path.

  1. Restart Claude Desktop.

For LM Studio

  1. Add the same configuration to LM Studio's mcp.json file:
{
  "mcpServers": {
    "blender": {
      "command": "python",
      "args": ["C:/path/to/chat-with-blender/run_server.py"]
    }
  }
}
  1. Restart LM Studio.

💡 Usage

1. Start the Server in Blender

  1. Open Blender
  2. Go to View3D → Sidebar (N key) → BlenderMCP tab
  3. Click the "Start Server" button
  4. You should see Status: Running

<p align="center"> <img src="screenshots/blender-panel.png" alt="BlenderMCP Panel" width="600"> </p>

2. Start Chatting with AI

Start a new chat in Claude Desktop or LM Studio and give Blender commands:

<p align="center"> <img src="screenshots/chat-demo.png" alt="AI Chat Demo" width="600"> </p>

Example Prompts

"Add a red metallic cube to the scene"

"Create a blue sphere next to the cube and move it 2 units to the right"

"Clear the scene and set up a studio: 
 ground, 3-point lighting, and camera"

"Create an emissive green torus, make it glow"

"Give me a list of all objects in the scene"

"Render the scene at 1920x1080 resolution"

💡 Tip: To see materials, set the viewport shading mode to Material Preview or Rendered in Blender (Z key).


🛠️ MCP Tools

Tool Description
get_scene_info Get scene information (objects, frame info)
get_object_info Get details of a specific object
create_object Create new primitive object (cube, sphere, cylinder...)
create_text Create 3D text
modify_object Modify object position/rotation/scale
delete_object Delete object
duplicate_object Duplicate object
apply_material Create and apply material
create_light Add light (POINT, SUN, SPOT, AREA)
create_camera Add camera
clear_scene Clear the scene
set_background_color Set background color
execute_blender_code Execute custom Python code
render_image Render image

🔒 Security

⚠️ Security Warning: This MCP server includes the execute_blender_code tool. This tool allows the AI to execute arbitrary Python code within Blender.

Security Recommendations

  1. Use trusted AI models - Only use with AI assistants you trust
  2. Localhost connection - Server runs on localhost by default
  3. Backup your important files - Save your Blender projects regularly
  4. Code review - Review the code that AI will execute beforehand

Network Security

  • Server listens only on localhost:9876
  • External access is disabled by default
  • No firewall rules needed

🐛 Known Issues and Limitations

This is a vibe coding project. The following known issues/limitations exist:

Issue Status Workaround
Materials not visible in viewport Expected behavior Switch to Material Preview mode with Z key
Blender 5.0+ node compatibility issues Fixed Use latest addon.py
Performance for complex models Known Start with simple objects

If you find a new bug, please open an Issue!


🐛 Troubleshooting

"Could not connect to Blender"

  • ✅ Make sure the addon is active in Blender
  • ✅ Click "Start Server" in the BlenderMCP panel
  • ✅ Check that port 9876 is not being used by another application

"ModuleNotFoundError: No module named 'blender_mcp'"

  • ✅ Make sure you're using the full path to the run_server.py file
  • ✅ Install Python dependencies: pip install mcp httpx

Materials not showing

  • ✅ Set viewport shading mode to Material Preview or Rendered (Z key)

Claude Desktop not showing tools

  • ✅ Check the path in the config file
  • ✅ Completely close and restart Claude Desktop

📁 Project Structure

chat-with-blender/
├── addon.py              # Blender addon (socket server)
├── run_server.py         # MCP server launcher
├── pyproject.toml        # Python project configuration
├── README.md             # This file
├── LICENSE               # MIT License
├── screenshots/          # Screenshots
└── src/
    └── blender_mcp/
        ├── __init__.py
        └── server.py     # MCP server implementation

🤝 Contributing

This is a vibe coding project - your contributions will make it more stable!

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

We especially need:

  • 🐛 Bug fixes
  • 📝 Documentation improvements
  • ✨ New MCP tools
  • 🧪 Test coverage

📄 License

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


🙏 Acknowledgments


<p align="center"> <strong>⭐ Don't forget to star this project if you like it!</strong> </p>

<p align="center"> <sub>Made with 💜 and lots of vibes</sub> </p>

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