ahujasid/mcp-for-blender

Community plugin to control Blender 3D with any LLM of your choice

What it solves

This project provides a bridge between Large Language Models (LLMs) and Blender, allowing users to perform 3D modeling, scene creation, and object manipulation using natural language prompts. It eliminates the need for users to manually navigate complex 3D software interfaces or write Python scripts by hand to achieve specific scene results.

How it works

The system uses the Model Context Protocol (MCP) to enable two-way communication between an AI client (like Claude Desktop or Cursor) and Blender. It consists of two primary components:

  1. Blender Addon: A plugin that runs inside Blender, creating a socket server to receive and execute commands.
  2. MCP Server: A Python-based server that implements the MCP standard, acting as the intermediary that translates LLM requests into commands the Blender addon can execute.

Who it’s for

3D artists, designers, and developers who want to automate 3D scene construction and manipulation using AI, or those who want to lower the barrier to entry for complex 3D modeling tasks.

Highlights

  • Direct Object Control: Create, modify, and delete 3D objects and apply materials/colors via AI prompts.
  • Arbitrary Code Execution: The AI can run any Python code directly within Blender to perform advanced tasks.
  • Asset Integration: Integrated search and download capabilities for assets from Poly Haven, Sketchfab, and Poly Pizza.
  • AI 3D Generation: Support for AI-generated 3D models via Hyper3D Rodin and Hunyuan3D.
  • Scene Inspection: The AI can query detailed information about the current Blender scene to make informed adjustments.
  • Safe Mode: An optional security setting that validates scripts to block risky operations like unauthorized file access or network calls.

Related

  • Project
    Anil-matcha/Open-Generative-AI

    An unrestricted, open-source AI studio for generating images, videos, and audio using 400+ models without content filters or subscription fees.

  • Project
    OpenBMB/MiniCPM-V

    A series of pocket-sized multimodal LLMs designed for efficient on-device deployment, enabling high-performance image, video, and real-time omnimodal interaction on mobile phones.

  • Project
    OpenBMB/ChatDev

    ChatDev 2.0 (DevAll) is an open‑source, zero‑code platform that lets you design and run multi‑LLM‑agent workflows via a visual web console or a tiny Python SDK. Define agents and their connections in YAML, launch from the browser or code, and use built‑in templates for data viz, 3‑D generation, game dev, research, etc. The backend is FastAPI, the frontend Vue 3, and the project ships Docker/Makefile support, extensible Python tools, and research‑grade orchestrators (Puppeteer, MacNet).

  • Project
    huggingface/diffusers

    A modular library for using and training state-of-the-art diffusion models to generate images, audio, and 3D molecular structures.