Connect Blender with Claude AI for prompt-driven 3D modeling and scene creation
BlenderMCP integrates Blender, a powerful 3D modeling software, with Claude AI through the Model Context Protocol (MCP), enabling real-time interaction between the two applications. This integration provides a seamless way to leverage AI prompts for creating, manipulating, and managing 3D scenes directly within Blender. By connecting these tools, users can achieve sophisticated workflows where AI suggestions inform and refine their modeling processes.
BlenderMCP offers several key features that enhance the capabilities of both MCP clients and Blender:
Two-way Communication: The server enables real-time data exchange between the AI application (such as Claude Desktop) and Blender. Commands can be issued from the AI client to manipulate 3D scenes, while actions taken within Blender trigger confirmations or additional requests back to the AI.
Object Manipulation: Users can create, modify, delete, move, rotate, and scale objects within Blender based on AI prompts.
Material Control: The ability to apply and modify materials directly through API commands from the AI application, allowing for rich texturing and shading effects.
Scene Inspection: Detailed information about the current 3D scene can be retrieved by the AI to better understand or respond to the context of ongoing modeling tasks.
Code Execution: Arbitrary Python code execution within Blender is supported, enabling advanced automation and customization possibilities.
The following Mermaid diagram illustrates the communication flow between the MCP client (e.g., Claude Desktop) and the server.
graph TD
A[AI Application] -->|MCP Client| B[MCP Server]
B --> C[Blender Addon]
C --> D[Blender Scene & Data]
style A fill:#e1f5fe
style B fill:#f3e5f5
style C fill:#e8f5e8
The protocol used by BlenderMCP is a JSON-based message exchange over TCP sockets. Commands sent from the MCP client to the server are structured as JSON objects containing type
and optional params
. Responses are also JSON formatted with fields like status
, result
, or message
.
To set up BlenderMCP, ensure you meet the following requirements:
On Mac:
brew install uv
On Windows:
irm https://astral.sh/uv/install.ps1 | iex
set Path=C:\Users\nntra\.local\bin;%Path%
Otherwise, follow the official UV installation documentation.
For users of MCP clients such as Claude Desktop and Continue:
Edit Configuration: In "Settings > Developer > Edit Config", add the mcpServers
section with the appropriate command and arguments.
{
"mcpServers": {
"blender": {
"command": "uvx",
"args": [
"blender-mcp"
]
}
}
}
addon.py
from this repository.Install...
and choosing the downloaded file.BlenderMCP serves several important use cases:
AI Assisted Modeling: Users can generate detailed 3D scenes from textual descriptions using AI prompts, streamlining complex modeling tasks.
"Create a cozy beachside cabin with palm trees, waves, and colorful sunsets."
Material Design Automation: Automate the application of materials based on design guidelines provided by an AI.
"Add a gold metallic finish to all metal objects in the scene and ensure shadows cast correctly."
BlenderMCP works seamlessly with multiple MCP clients:
Claude Desktop: Offers full support for Blender integration.
The compatibility matrix indicates which MCP clients work best with BlenderMCP:
MCP Client | Resources | Tools | Prompts |
---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ |
Continue | ✅ | ✅ | ✅ |
Cursor | ❌ | ✅ | ❌ |
Execution Safety: The execute_blender_code
feature allows running arbitrary Python code, making it powerful yet potentially dangerous. Always be cautious when using this tool in production environments.
Poly Haven Integration: Enabling Poly Haven adds support for downloading assets through API calls.
{
"mcpServers": {
"blender": {
"command": "uvx",
"args": [
"blender-mcp"
]
}
},
"poly_haven_assets_enabled": true,
"hyper3d_api_key": "your_hyper3d_api_key"
}
Connection Issues: Ensure that both the Blender addon server and the MCP client are running, and double-check configurations.
Timeout Errors: Simplify your requests or break them into smaller steps to reduce latency.
Poly Haven Integration: While useful for asset downloads, this feature can sometimes behave erratically. Consider alternative resources if issues persist.
Complex Operations: Break down complex tasks into manageable steps to avoid overwhelming the protocol stack.
Stability Concerns: Regularly restart both Blender and the MCP server when encountering persistent errors or crashes.
Contributions are warmly welcomed. Please submit issues, pull requests, or improve documentation through GitHub.
Explore more about Model Context Protocol (MCP) in various applications from the official documentation. For continuous support and community updates, join our Discord server: Discord.
By integrating Blender with MCP servers like BlenderMCP, developers can unlock new levels of efficiency and creativity in their AI-driven workflows.
Learn to connect to MCP servers over HTTP with Python SDK using SSE for efficient protocol communication
Explore community contributions to MCP including clients, servers, and projects for seamless integration
Python MCP client for testing servers avoid message limits and customize with API key
SingleStore MCP Server for database querying schema description ER diagram generation SSL support and TypeScript safety
Next-generation MCP server enhances documentation analysis with AI-powered neural processing and multi-language support
Powerful GitLab MCP Server enables AI integration for project management, issues, files, and collaboration automation