Blender Open
A server that integrates Blender with local AI models via the Model Context Protocol, allowing users to control Blender using natural language prompts for 3D modeling tasks.
What is Blender Open?
Blender Open is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to server that integrates blender with local ai models via the model context protocol, allowing users to control blender using natural language prompts for 3d modeling tasks.
A server that integrates Blender with local AI models via the Model Context Protocol, allowing users to control Blender using natural language prompts for 3D modeling tasks.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A server that integrates Blender with local AI models via th
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx blender-open-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Blender Open
Blender Open MCP is a Python-based MCP server and Blender add-on that connects AI assistants to Blender 3D via local Ollama language models, enabling natural language control of 3D modeling tasks including object creation, modification, material assignment, rendering, and PolyHaven asset management. Unlike cloud-based Blender integrations, it runs entirely locally — the MCP server communicates with Blender through a socket add-on on port 9876 and uses Ollama (default: llama3.2) for model inference, making it suitable for users who want offline AI-powered 3D automation.
Prerequisites
- Blender 3.x or 4.x installed
- Python 3.10+ and uv package manager installed
- Ollama installed and running locally (https://ollama.com) with at least one model pulled (e.g., llama3.2)
- Git to clone the repository
- An MCP-compatible client such as Claude Desktop or Cursor
Clone the repository and set up the Python environment
Clone the blender-open-mcp repository, create a uv virtual environment, and install the package in editable mode.
git clone https://github.com/dhakalnirajan/blender-open-mcp.git
cd blender-open-mcp
uv venv
source .venv/bin/activate
uv pip install -e .Install the Blender socket add-on
In Blender, open Edit > Preferences > Add-ons > Install, and select the add-on file from the cloned repository. Enable the add-on to start the socket server on port 9876 inside Blender.
Start Ollama with your preferred model
Ensure Ollama is running and the desired model is available. The default model is llama3.2.
ollama serve
ollama pull llama3.2Configure your MCP client to launch the server
Add the blender-open-mcp server to your MCP client configuration. Use the blender-mcp command installed by the package with stdio transport.
Test with a natural language 3D command
With Blender open and the add-on active, send a natural language prompt through your MCP client. The server will translate it to Blender Python (bpy) code and execute it.
blender-mcp-client prompt "Create a metallic sphere at position 0, 0, 2"Blender Open Examples
Client configuration
Claude Desktop or Cursor MCP config launching the blender-open-mcp server in stdio mode.
{
"mcpServers": {
"blender-open-mcp": {
"command": "blender-mcp",
"args": ["--transport", "stdio"],
"env": {
"OLLAMA_MODEL": "llama3.2",
"OLLAMA_URL": "http://localhost:11434"
}
}
}
}Prompts to try
Example prompts demonstrating natural language 3D modeling and Blender automation.
- "Create a red metallic sphere at the origin with a radius of 1.5"
- "Add a wooden texture to the selected object using a PolyHaven material"
- "Delete all objects in the scene and set up a simple studio lighting rig"
- "Render the current scene with Cycles and save it to /tmp/render.png"
- "List all objects in the current Blender scene and describe their positions"
- "Create a low-poly mountain landscape with 3 peaks"Troubleshooting Blender Open
Connection refused on port 9876 — Blender add-on not responding
Ensure Blender is open with the socket add-on installed and enabled via Edit > Preferences > Add-ons. The add-on must be active in Blender for the MCP server to communicate with it. Restart Blender and re-enable the add-on if needed.
Ollama model not found or inference errors
Run 'ollama list' to confirm the model is downloaded. Pull it with 'ollama pull llama3.2' (or your preferred model). Ensure Ollama is running with 'ollama serve' before starting the MCP server. Update the --ollama-model argument if using a different model.
blender-mcp command not found after installation
Ensure the uv virtual environment is activated (source .venv/bin/activate) and the package was installed with 'uv pip install -e .'. The blender-mcp entry point is registered during install. Run 'which blender-mcp' to verify the binary is on your PATH.
Frequently Asked Questions about Blender Open
What is Blender Open?
Blender Open is a Model Context Protocol (MCP) server that server that integrates blender with local ai models via the model context protocol, allowing users to control blender using natural language prompts for 3d modeling tasks. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Blender Open?
Follow the installation instructions on the Blender Open GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Blender Open?
Blender Open works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Blender Open free to use?
Yes, Blender Open is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Blender Open Alternatives — Similar Developer Tools Servers
Looking for alternatives to Blender Open? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Blender Open in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Blender Open?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.