mcp-for-blender: Prompt-assisted 3D modeling, scene creation, and manipulation — driven by AI.
What problem it solves
Users need a way to connect an LLM client to Blender so they can create, inspect, and modify 3D scenes through natural-language instructions. The integration also needs a bidirectional connection, a socket-based Blender addon, and an MCP server that works with multiple AI applications.
Key features
Two-way Blender communication — The integration connects an AI client to Blender through a socket-based server, allowing commands to travel between the client and the live Blender session.
Source: README
Scene and object manipulation — Users can ask an AI to create, modify, and delete 3D objects, apply materials, and perform modeling, layout, animation, rigging, and retopology work.
Source: README
Visual verification — The AI can inspect its work through viewport, camera, multi-angle, wireframe, X-ray, animation-strip, and rendered views.
Source: README
AI-assisted Python execution — The integration lets the AI write Blender Python and execute it in the live Blender environment.
Source: README
Asset and model access — The plugin connects Blender with Poly Haven assets, Sketchfab and Poly Pizza models, plus AI-generated model providers.
Source: README
Quick start
Copied verbatim from the project's README.
curl -LsSf https://www.mcp-for-blender.com/install.sh | shirm https://www.mcp-for-blender.com/install.ps1 | iex{
"mcpServers": {
"blender": {
"command": "uvx",
"args": ["mcp-for-blender"]
}
}
}Who it may suit
Inference: This project may suit Blender users who want natural-language assistance with modeling, scene setup, materials, animation, rigging, and visual verification through an MCP-compatible AI client.
Topics to discuss
Which Blender workflows would benefit most from prompt-assisted modeling and scene manipulation?
How should safe mode balance direct Python execution with restrictions on risky operations?
Which MCP client integrations and visual verification workflows should the community prioritize next?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/ahujasid/mcp-for-blender#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…