Blender Open MCP MCP server

Integrates Blender with local AI models via Ollama, enabling natural language control of 3D modeling tasks including object creation, modification, material application, and rendering with optional PolyHaven asset integration.
Back to servers
Provider
Nirajan Dhakal
Release date
Mar 14, 2025
Language
Python
Stats
26 stars

Blender Open MCP integrates Blender with local AI models through Ollama, allowing you to control Blender using natural language prompts. This implementation of the Model Context Protocol (MCP) establishes structured communication between AI models and Blender, enabling you to perform 3D modeling tasks through conversational commands.

Prerequisites

Before installing Blender Open MCP, ensure you have:

  • Blender 3.0 or later from blender.org
  • Ollama installed from ollama.com
  • Python 3.10 or later
  • The uv package (install with pip install uv)
  • Git for repository cloning

Installation

Set Up the MCP Server

  1. Clone the repository and navigate to the project directory:
git clone https://github.com/dhakalnirajan/blender-open-mcp.git
cd blender-open-mcp
  1. Create and activate a virtual environment:
uv venv
source .venv/bin/activate  # On Linux/macOS
.venv\Scripts\activate  # On Windows
  1. Install the dependencies:
uv pip install -e .

Install the Blender Add-on

  1. Open Blender
  2. Navigate to Edit → Preferences → Add-ons
  3. Click "Install..."
  4. Browse to and select the addon.py file from the blender-open-mcp directory
  5. Enable the "Blender MCP" add-on by checking its box

Set Up an Ollama Model

If you haven't already installed a model, run:

ollama run llama3.2

You can also use other models like Gemma3.

Starting the Services

Launch the MCP Server

Start the server using one of these methods:

blender-mcp

Or alternatively:

python src/blender_open_mcp/server.py

You can customize the server settings:

blender-mcp --host 127.0.0.1 --port 8001 --ollama-url http://localhost:11434 --ollama-model llama3.2

Activate the Blender Add-on

  1. Open Blender and the 3D Viewport
  2. Press N to open the sidebar
  3. Find the "Blender MCP" panel
  4. Click "Start MCP Server"

Using Blender Open MCP

You can interact with Blender through natural language commands using the mcp CLI tool.

Basic Commands

Get general information:

mcp prompt "Hello BlenderMCP!" --host http://localhost:8000

Retrieve scene details:

mcp tool get_scene_info --host http://localhost:8000

Create a new object:

mcp prompt "Create a cube named 'my_cube'." --host http://localhost:8000

Render your scene:

mcp prompt "Render the image." --host http://localhost:8000

Access PolyHaven assets (if enabled):

mcp prompt "Download a texture from PolyHaven." --host http://localhost:8000

Available Tools and Functions

Scene Management

  • get_scene_info: Retrieves overall scene information
  • get_object_info: Gets details about a specific object by name

Object Operations

  • create_object: Creates 3D objects with specified type, name, location, rotation, and scale
  • modify_object: Adjusts an object's properties including position, rotation, scale, and visibility
  • delete_object: Removes objects from the scene

Materials and Textures

  • set_material: Assigns materials to objects with color properties
  • set_texture: Applies downloaded textures to objects

Rendering

  • render_image: Renders an image to a specified file path

Advanced Functions

  • execute_blender_code: Executes Python code directly in Blender

PolyHaven Integration

  • get_polyhaven_categories: Lists available asset categories
  • search_polyhaven_assets: Searches for assets by type and category
  • download_polyhaven_asset: Downloads assets with customizable resolution and format

Ollama Configuration

  • set_ollama_model: Changes the active Ollama model
  • set_ollama_url: Updates the Ollama server URL
  • get_ollama_models: Lists all available Ollama models

Troubleshooting

If you encounter issues:

  • Verify that both Ollama and the Blender Open MCP server are running
  • Check that the Blender add-on is properly installed and activated
  • Confirm your command-line arguments match your server configuration
  • Review the server logs for detailed error information

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later