Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Blender Server

FreeNot checked

A Python-based MCP server for integrating Blender and 3D modeling capabilities with OpenClaw AI agents.

GitHubEmbed

About

A Python-based MCP server for integrating Blender and 3D modeling capabilities with OpenClaw AI agents.

README

A Python-based Model Context Protocol (MCP) server for integrating Blender and 3D modeling capabilities with OpenClaw AI agents. This project aims to adapt and deploy blender-mcp as a dedicated MCP server for our AI Comic Studio's Phase 2 development.

Disclaimer: This is an adaptation of the original blender-mcp project. We have no official affiliation with the original blender-mcp project or its maintainers.

Features

  • Blender Control: Interact with Blender to create, modify, and delete 3D objects, control materials, and inspect scenes.
  • AI-powered 3D Generation: Integrate with AI 3D generation tools like Hunyuan3D and Hyper3D Rodin (via their APIs).
  • Asset Management: Download models from Sketchfab and assets from Poly Haven.
  • Python Code Execution: Execute arbitrary Python code within Blender.

Components

This project will adapt and contain the following core components from the original blender-mcp:

  1. Blender Addon (addon.py): A Blender addon that creates a socket server within Blender to receive and execute commands. (Will be placed in the root of this repo for easy access)
  2. MCP Server (src/blender_mcp/server.py): The Python server that implements the Model Context Protocol and connects to the Blender addon.

Installation and Setup (Local Development)

Prerequisites

  • Blender 3.0 or newer
  • Python 3.10 or newer
  • uv package manager (recommended for dependency management)

Environment Setup

  1. Clone the repository:
    git clone https://github.com/tinhtinhcd/mcp-blender-server
    cd mcp-blender-server
    
  2. Install uv (if not already installed):
    curl -LsSf https://astral.sh/uv/install.sh | sh
    export PATH="$HOME/.local/bin:$PATH" # Add uv to PATH for current session
    
  3. Create a virtual environment and install dependencies:
    uv venv
    source ./.venv/bin/activate # Activate the virtual environment
    uv pip install "mcp[cli]>=1.3.0" "supabase>=2.0.0" "tomli>=2.0.0"
    
    (Note: Additional dependencies from the original blender-mcp project may be added as needed.)

Running the MCP Server

To run the MCP server:

uvx mcp-blender-server

(Ensure your Blender addon is also running and connected.)

Integration with OpenClaw AI Agent

This server will be configured as an MCP server for an OpenClaw AI agent. The AI agent will send commands to this server to control Blender and manage 3D assets.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

from github.com/tinhtinhcd/mcp-blender-server

Install Blender Server in Claude Desktop, Claude Code & Cursor

Recommended · one command, every IDE
unyly install mcp-blender-server

Installs into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.

First time? Get the CLI: curl -fsSL https://unyly.org/install | sh

Or configure manually

Run in your terminal:

claude mcp add mcp-blender-server -- uvx --from git+https://github.com/tinhtinhcd/mcp-blender-server mcp-blender-server

FAQ

Is Blender Server MCP free?

Yes, Blender Server MCP is free — one-click install via Unyly at no cost.

Does Blender Server need an API key?

No, Blender Server runs without API keys or environment variables.

Is Blender Server hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Blender Server in Claude Desktop, Claude Code or Cursor?

Open Blender Server on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Blender Server with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All ai MCPs