BlenderMCP
Connects Claude AI to Blender through the Model Context Protocol, enabling AI-assisted 3D modeling, scene creation, object manipulation, and material control. Supports downloading assets from Poly Haven and generating 3D models through Hyper3D Rodin.
README
Blender MCP (Model Context Protocol)
A Blender addon that enables AI assistants (like Claude) to interact with Blender through the Model Context Protocol (MCP).
Installation
1. Install the Blender Addon
-
Download or clone this repository
-
Copy the entire
src/blender_mcp/addon/directory to your Blender addons folder:- Windows:
%APPDATA%\Blender Foundation\Blender\4.x\scripts\addons\ - macOS:
~/Library/Application Support/Blender/4.x/scripts/addons/ - Linux:
~/.config/blender/4.x/scripts/addons/
- Windows:
-
Rename the copied directory from
addontoblender_mcp -
Open Blender and go to
Edit > Preferences > Add-ons -
Search for "Blender MCP" and enable the addon
2. Install the MCP Server
The MCP server runs outside Blender and communicates with it via sockets.
-
Install Python dependencies:
pip install mcp-server-fastmcp -
Or if using the provided virtual environment:
# Activate the virtual environment source .venv/bin/activate # On Windows: .venv\Scripts\activate # Install dependencies pip install -r requirements.txt
3. Configure Your MCP Client
Add the Blender MCP server to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": {
"blender": {
"command": "python",
"args": ["-m", "blender_mcp.server"],
"env": {
"BLENDER_HOST": "localhost",
"BLENDER_PORT": "9876"
}
}
}
}
Usage
- Start Blender and enable the Blender MCP addon
- Start your MCP client (Claude Desktop, etc.) with the server configured
- In Blender, click the "Connect to MCP server" button in the BlenderMCP panel (N-panel > BlenderMCP)
- Use Claude to interact with Blender through natural language commands
Features
Core Tools
- Scene Information: Get details about objects, materials, and scene structure
- Object Manipulation: Query and modify 3D objects
- Viewport Screenshots: Capture Blender's 3D viewport
- Code Execution: Run Python code directly in Blender
Template Engine
- Template Management: Create, save, and reuse complex operations
- Dynamic Overrides: Apply templates with parameter modifications
- Template Search: Discover templates by tags and categories
- Usage Analytics: Track template performance and success rates
- Version Control: Optional Git versioning for template evolution
Asset Integrations
- PolyHaven: Download HDRIs, textures, and 3D models
- Sketchfab: Search and download 3D models
- Hyper3D Rodin: Generate 3D models from text or images
Configuration
Blender Addon Settings
- Port: Socket port for communication (default: 9876)
- PolyHaven: Enable/disable PolyHaven integration
- Hyper3D: Configure API keys and modes
- Sketchfab: Configure API key for model downloads
Environment Variables
BLENDER_HOST: Host address (default: localhost)BLENDER_PORT: Port number (default: 9876)
Architecture
The system consists of two main components:
- Blender Addon (
src/blender_mcp/addon/): Runs inside Blender, handles UI and executes Blender operations - MCP Server (
src/blender_mcp/server/): Runs outside Blender, provides MCP tools and manages communication
Development
Project Structure
src/blender_mcp/
├── addon/ # Blender addon code
│ ├── handlers.py # Base command handlers
│ ├── polyhaven_handlers.py # PolyHaven integration
│ ├── hyper3d_handlers.py # Hyper3D integration
│ ├── sketchfab_handlers.py # Sketchfab integration
│ ├── ui.py # Blender UI components
│ ├── server.py # Socket server for addon
│ └── __main__.py # Addon registration
└── server/ # MCP server code
├── connection.py # MCP server and socket client
├── tools.py # Core Blender tools
├── integrations.py # Integration tools
├── template_engine.py # Template storage and management
├── template_tools.py # MCP tools for templates
├── prompts.py # MCP prompts
└── __main__.py # Server entry point
templates/ # Template storage directory
├── template_name.json # Template definitions
└── analytics.json # Usage statistics
Running Tests
# Test server modules
python -m pytest tests/
# Or manually test imports
python -c "from src.blender_mcp.server.connection import mcp; print('OK')"
Troubleshooting
Connection Issues
- Ensure the Blender addon is enabled and running
- Check that the port numbers match between client and server
- Verify firewall settings allow socket connections
Integration Issues
- Check API keys are properly configured in Blender
- Ensure internet connectivity for external services
- Review Blender console for error messages
Performance
- Large scenes may take time to process
- Asset downloads depend on internet speed
- 3D generation can take several minutes
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Test thoroughly
- Submit a pull request
License
See LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.