AI-Powered 3D Modeling with Blender MCP

Transform your 3D workflow with natural language instructions

Blender MCP connects Claude AI to Blender, allowing you to create, modify, and enhance 3D models through simple text prompts.

Blender MCP also supports built-in Blender plugins, enhancing your 3D modeling capabilities with native tools.

Get Started Watch Demo
Blender MCP Claude MCprep addon
Enhance Blender MCP's advanced 3D modeling features with MCprep addon
Blender MCP Cursor Interface
Configure Blender MCP in Cursor Mode for precise 3D modeling control
Blender MCP Windsurf Model Example
Configure Blender MCP in Windsurf Mode for professional modeling results
Blender MCP VSCode Roo Plugin Installation
Blender MCP VSCode Roo Cline Install
Blender MCP VSCode Roo Plugin Key Setting
Blender MCP VSCode Roo Cline Set Key
Blender MCP VSCode Roo Plugin MCP Configuration
Blender MCP VSCode Roo Cline MCP

Key Features

AI-Powered Modeling

Create and modify 3D objects in Blender using natural language instructions with Claude AI.

Python Code Execution

Run arbitrary Python code in Blender through simple text prompts for advanced customization.

Material Management

Apply and modify materials with AI assistance for stunning visual results.

Scene Control

Adjust camera positions, lighting, and scene properties with natural language commands.

Polyhaven Integration

Access and use Polyhaven assets directly through AI commands for enhanced 3D scenes.

Easy Integration

Seamless installation process and compatibility with Blender across multiple platforms.

Getting Started with Blender MCP

Blender MCP Setup Tutorial Thumbnail

Installation Guide

Prerequisites

  • Blender 3.0 or later
  • Python 3.10 or later
  • uv package manager

Install uv on Windows:

pip install uv

Install uv on Mac:

brew install uv

⚠️ Please install UV before proceeding

Claude for Desktop Integration

Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json and add the following:

{ "mcpServers": { "blender": { "command": "uvx", "args": [ "blender-mcp" ] } } }

MCP Integration in Different Environments

Cursor Integration
Blender MCP Cursor Integration

Go to Cursor Settings > MCP and paste the following command:

uvx blender-mcp
Windsurf Integration
Blender MCP Windsurf Integration

In Windsurf, the MCP server is pre-configured. Just enable the plugin in Blender and connect.

VSCode Integration (using Roo Cline)
VSCode Roo Cline Installation

1. Install the Roo Cline extension in VSCode

VSCode Roo Cline Set API Key

2. Set your API key

VSCode Roo Cline MCP Configuration

3. Configure the MCP server with the command uvx blender-mcp

⚠️ Important: Only run one MCP server instance (in Cursor, Windsurf, VSCode, or Claude Desktop), not multiple instances simultaneously

Installing the Blender Plugin

  1. Download the addon.py file from the GitHub repository
  2. Open Blender
  3. Go to Edit > Preferences > Add-ons
  4. Click "Install..." and select the addon.py file
  5. Enable the plugin by checking the box next to "Interface: Blender MCP"
Blender MCP Plugin Installation

Installing the Blender MCP addon

Blender MCP Plugin Configuration

Configuring the Blender MCP addon

Usage Instructions

Starting the Connection

  1. In Blender, go to the 3D View sidebar (press N if not visible)
  2. Find the "BlenderMCP" tab
  3. Check the Poly Haven checkbox if you want to use Poly Haven assets (optional)
  4. Click "start mcp server"
  5. Make sure the MCP server is running in your terminal

Using with Claude

Once the config file is set up in Claude and the plugin is running in Blender, you'll see a hammer icon with Blender MCP tools.

Example Commands

  • "Create a low poly scene in a dungeon, with a dragon guarding a pot of gold"
  • "Create a beach vibe using HDRIs, textures, and models like rocks and vegetation from Poly Haven"
  • "Get information about the current scene, and make a threejs sketch from it"
  • "Make this car red and metallic"
  • "Create a sphere and place it above the cube"
  • "Make the lighting like a studio"
  • "Point the camera at the scene, and make it isometric"
Watch Full Setup Tutorial

See Blender MCP in Action

Blender MCP Demo Video Thumbnail

Transform 2D references into 3D models with AI

In this demonstration, you'll see how Blender MCP allows you to provide a 2D reference image and have Claude AI generate a 3D model in Blender — all through natural language conversation.

No manual modeling required
Iterate rapidly through prompts
Fine-tune with precise instructions
Watch on YouTube See more demos

Use Cases

Concept Artist using Blender MCP

Concept Artists

Rapidly prototype 3D concepts from sketches or descriptions, accelerating the conceptualization process.

Learn more
Game Developer using Blender MCP

Game Developers

Create game assets quickly with natural language descriptions, streamlining the development pipeline.

Learn more
Educator using Blender MCP

Educators

Teach 3D modeling concepts with an accessible interface that lowers the technical barrier for students.

Learn more
Architectural Visualizer using Blender MCP

Architectural Visualizers

Generate 3D architectural elements and environments from textual descriptions or reference images.

Learn more
Minecraft Scene created with Blender MCP

Minecraft Modeling

Create stunning Minecraft-style 3D scenes in just 10 minutes using natural language prompts, even with no prior Blender experience.

What You'll Learn:

  • Create natural terrain with Perlin noise
  • Design Minecraft-style buildings
  • Add trees, rivers, and weather effects
  • Use the MCPrep plugin for authentic Minecraft assets
  • Model Minecraft characters like Alex

Requirements:

  • Blender with MCPrep plugin
  • Blender MCP setup
  • No prior experience needed!
Start Tutorial

How Blender MCP Works

1

Install the Plugin

Download the Blender MCP plugin from GitHub and install it in your Blender application.

Download Plugin
2

Configure MCP Server

Set up the MCP server to establish communication between Claude AI and Blender.

View Setup Guide
3

Start Creating with AI

Use natural language instructions to create and modify 3D models in Blender through Claude.

See Examples

DeepSeek Integration

Using DeepSeek R1 and Claude 3.7 Sonnet Models

Blender MCP not only supports Claude but also other large language models like DeepSeek R1. Through OpenRouter.ai, you can easily switch between different models for 3D modeling.

Setup Steps

  1. Register for an OpenRouter.ai Account

    Visit OpenRouter.ai and create an account.

  2. Get an API Key

    Generate an API key in your OpenRouter account, which you'll need to configure different models.

  3. Configure VSCode to Use Different Models

    Follow these steps to configure DeepSeek R1 and Claude 3.7 Sonnet models in VSCode:

VSCode DeepSeek Profile Configuration

Create DeepSeek Profile

VSCode DeepSeek Model Configuration

Configure DeepSeek Model Parameters

VSCode Model Switching

Switch Between DeepSeek R1 and Claude 3.7 Sonnet

Steps to Use Different Models

  1. Open the Roo Cline extension settings in VSCode
  2. Create two different profiles: one for DeepSeek R1 and one for Claude 3.7 Sonnet
  3. Set the corresponding model ID in each profile:
    • DeepSeek R1: deepseek-ai/deepseek-coder-v2
    • Claude 3.7 Sonnet: anthropic/claude-3-7-sonnet
  4. Add your OpenRouter API key
  5. Configure the MCP server command: uvx blender-mcp
  6. Save the configuration and use the dropdown menu to switch between models

Model Comparison

Feature DeepSeek R1 Claude 3.7 Sonnet
Strengths Code generation, technical understanding Creative design, natural language understanding
Response Speed Faster Moderate
3D Modeling Capability Good geometric understanding Excellent creative expression

Usage Tips

  • For precise geometric shapes and technical modeling, try DeepSeek R1
  • For creative scenes and artistic effects, try Claude 3.7 Sonnet
  • Both models can use the same set of Blender MCP commands
  • Reconnect the Blender MCP server after switching models
  • Save your work, as different models may produce different results for the same prompt

Other MCP Integrations

Combining Blender MCP with Server-Sequential-Thinking

Enhance your 3D modeling workflow by combining Blender MCP with other MCP tools like server-sequential-thinking. This powerful combination allows for complex modeling tasks with step-by-step planning and execution.

Integration Benefits

  • Break down complex modeling tasks into sequential steps
  • Improve planning and execution of detailed 3D models
  • Monitor and modify each step for optimal results
  • Create more sophisticated structures with better organization

Example Workflow: Creating a High-Rise Building

Here's an example of how to use server-sequential-thinking with Blender MCP to create a complex high-rise building model:

Prompt: "I want to use Blender to create a high-rise building. Please use server-sequential-thinking tool to help me generate all the operation steps, then use blender-mcp to execute the generation. Remember to monitor each modification, and if there's anything unreasonable, make timely adjustments. Please also add a larger pavilion next to the existing one."
How It Works:
  1. Planning Phase (server-sequential-thinking): The sequential thinking server breaks down the complex task into logical steps:
    • Step 1: Create the base structure of the high-rise building
    • Step 2: Add floors and windows to the building
    • Step 3: Design the roof structure
    • Step 4: Create the existing pavilion
    • Step 5: Add a larger pavilion next to the existing one
    • Step 6: Add environmental details and finishing touches
  2. Execution Phase (blender-mcp): Blender MCP executes each step with appropriate Python code
  3. Monitoring Phase: The system checks each modification for quality and makes adjustments as needed

Tool Comparison

Feature Blender MCP Server-Sequential-Thinking
Primary Function 3D model execution in Blender Step-by-step planning and reasoning
Strengths Direct model manipulation Complex task breakdown
Best Used For Creating and modifying 3D objects Planning complex modeling workflows

Integration Tips

  • Start with server-sequential-thinking to plan your complex modeling task
  • Use the generated steps as a guide for Blender MCP execution
  • Monitor each step and make adjustments as needed
  • For architectural models, break down structures into logical components
  • Save intermediate results to track progress and allow for revisions

Getting Started with Server-Sequential-Thinking

To use server-sequential-thinking with Blender MCP:

  1. Install the server-sequential-thinking tool from GitHub
  2. Configure it to work with your existing Blender MCP setup
  3. Use prompts that specifically request sequential planning
  4. Review and approve the generated plan before execution

For more information, visit the Sequential Thinking GitHub repository.

Frequently Asked Questions

What is Blender MCP?

Blender MCP is a tool that connects Blender with Claude AI through the Model Context Protocol (MCP). It allows you to create, modify, and enhance 3D models in Blender through natural language instructions. It was developed by Siddharth Ahuja (ahujasid), who maintains the GitHub repository and shares tutorials on his YouTube channel.

Do I need a Claude subscription to use Blender MCP?

Yes, you need access to Claude AI through Anthropic, which requires a subscription. The MCP server connects your Blender instance to your Claude session.

Which versions of Blender are supported?

Blender MCP currently supports Blender 3.6 and newer. The plugin may work with older versions, but full functionality is not guaranteed.

Can I use Blender MCP for commercial projects?

Yes, Blender MCP is open-source and available for personal and commercial use. However, you should review Claude AI's terms of service regarding the commercial use of AI-generated content.

How accurate is the 3D modeling through natural language?

The accuracy depends on the clarity of your instructions and the complexity of the model. Simple objects and modifications work very well, while complex models may require iterative refinement through multiple prompts.

Is Blender MCP compatible with other 3D software?

Currently, Blender MCP is designed specifically for Blender. However, the MCP protocol could potentially be adapted for other 3D software in the future.

Where can I get help if I run into issues?

You can seek help by creating an issue on the GitHub repository, joining the community Discord, or checking the documentation for troubleshooting guides.

Can I contribute to the Blender MCP project?

Absolutely! The project is open-source and welcomes contributions. You can fork the repository, make improvements, and submit pull requests on GitHub.

How can I use Blender MCP with Claude API?

You can use VSCode to access Claude's API capabilities with Blender MCP. Install the VSCode extension, configure your Claude API key, and connect to the Blender MCP server. This setup allows you to send natural language instructions directly from VSCode to Blender through Claude's powerful language processing.

Which AI models are compatible with Blender MCP?

Blender MCP supports a wide range of large language models beyond Claude, including DeepSeek R1, Gemini 2.0 Flash Thinking, Qwen 32B, and many others. This flexibility allows you to choose the AI model that best suits your specific 3D modeling needs and preferences.

Can I use Blender MCP for free?

Yes! You can use Blender MCP for free by combining VSCode with OpenRouter's free models. These include google/gemini-2.0-flash-thinking-exp:free, deepseek/deepseek-r1-distill-llama-70b:free, qwen/qwen2.5-vl-72b-instruct:free, and others. This approach gives you access to powerful AI-assisted 3D modeling capabilities without any cost.

How can I use Blender MCP with DeepSeek/Ollama locally?

To use Blender MCP with local models through Ollama:

  1. Install Ollama: Download and install Ollama (supports Windows, MacOS, and Linux) from the Ollama official website or GitHub repository.
  2. Run the Ollama service (default port is localhost:11434).
  3. Pull models: Use the command line to run ollama pull <model_name> to download your desired model, such as ollama pull llama3 or ollama pull qwen2.5:7b.
  4. Verify models: Ensure the model has been successfully downloaded and can be viewed via ollama list.
  5. Configure Roo Code: Install the Roo Code extension in Visual Studio Code, open Roo Code settings, select "Ollama" as the API provider, and ensure the Base URL is set to http://localhost:11434 (Ollama's default address).
  6. Enter your downloaded model name (e.g., qwen2.5:7b or another pulled model).
  7. Test the connection: Enter a simple task in Roo Code's chat interface (e.g., "write a Python code") to check if it responds normally.
  8. Troubleshooting: If you encounter connection errors (such as "target machine actively refused connection"), ensure the Ollama service is running and the port is not occupied.

Ready to Transform Your 3D Workflow?

Start creating with Blender MCP today and experience the power of AI-assisted 3D modeling.

Download Now See Demos