- Home
- MCP servers
- Blender
Blender
- python
10
GitHub Stars
python
Language
4 months ago
First Indexed
3 weeks ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
You can run a Blender MCP Server that exposes 50+ Blender tools via a simple HTTP API, enabling AI-driven automation and orchestration of 3D workflows with safe, concurrent execution and automatic dependency setup.
How to use
Start by running the Blender MCP Server and then connect to it with an MCP client or PolyMCP-enabled agent. Once connected, you can issue natural language instructions that map to Blender actions, such as creating or transforming objects, configuring materials and shaders, animating scenes, setting up cameras and lights, applying physics simulations, and exporting assets. The server provides an API surface you can discover and invoke, with a built-in tool catalog you can query to understand available capabilities. Use the server’s documentation at its docs endpoint to understand each tool’s purpose and required inputs.
How to install
Prerequisites
- Blender 3.0 or higher installed on your machine
- Python 3.x compatible with Blender's bundled Python
Step 1: Download the Blender MCP Server addon
Step 2: Open Blender
Step 3: Go to Edit → Preferences → Add-ons
Step 4: Click the dropdown arrow next to the search bar
Step 5: Select Install from Disk...
Step 6: Choose the downloaded blender_mcp.py file
Step 7: Enable the addon by checking the box next to "MCP Complete Server for Blender"
Additional setup and usage notes
After enabling the addon, open the 3D Viewport, press N to reveal the sidebar, and use the MCP Server panel to start the server. By default, the server runs at http://localhost:8000. The addon will automatically install required dependencies (FastAPI, Uvicorn, Pydantic, docstring-parser, NumPy, PolyMCP) on first run.
Connecting with PolyMCP
To control Blender with AI, connect a PolyMCP agent to the Blender MCP Server. You can provide an LLM provider, specify the server URL, and begin sending natural language prompts. The agent handles task planning, tool selection, retries, and state management, allowing you to orchestrate complex Blender workflows from your AI interface.
Example commands you can run once connected
Create a cube at position (0, 0, 0) with size 2; add a red metallic material to the selected object; create a camera looking at the origin; set up a simple lighting scene with 3 lights; add a fluid simulation to the cube; export the scene as an FBX file; create an animation rotating the object 360 degrees over 100 frames.
API endpoints you can access
Access the API documentation at http://localhost:8000/docs. Retrieve the list of available tools at http://localhost:8000/mcp/list\_tools. Invoke a specific tool via POST to http://localhost:8000/mcp/invoke/{tool\_name}.
Security and reliability notes
The server employs a production-ready queue system to safely execute operations concurrently. It also includes error handling, logging, and result caching to improve reliability and performance. Regular monitoring of server status and operation statistics helps you detect issues early and adjust your workflow as needed.
Available tools
blend_api
Exposes Blender capabilities as MCP endpoints, covering Object Operations, Transformations, Materials, Animation, Camera and Lighting, Physics, Geometry Nodes, File Operations, Scene Management, and Batch Operations.