Blender MCP Setup Guides — Every Platform, Step by Step
Blender MCP connects AI to Blender 3D through the Model Context Protocol. Choose your AI client below and follow the step-by-step guide to get started. Every guide covers prerequisites, installation, configuration, troubleshooting, and example prompts.
All guides require:
- Blender 3.0 or newer
- The uv package manager
- ~5–10 minutes of setup time
Choose Your AI Client
| Guide | AI Client | Difficulty | Cost |
|---|---|---|---|
| Claude Setup | Claude Desktop / Claude Code | Easy | Free tier available |
| Cursor Setup | Cursor IDE | Easy | Free tier available |
| VSCode Setup | VSCode + Cline / Roo Code | Medium | Free |
| ChatGPT Setup | ChatGPT Desktop | Medium | ChatGPT Plus recommended |
| Gemini Setup | Google Gemini CLI | Medium | Free tier available |
| Ollama Setup | Local AI (Ollama) | Advanced | Completely free |
Most Popular
Claude is the recommended starting point — Blender MCP was designed for Claude, and it has the most mature integration. If you’re using Cursor for coding, the Cursor guide is your best bet.
Completely Free
Want to run everything locally with zero API costs? Follow the Ollama guide to run Blender MCP with a local AI model.
How It Works
Every setup follows the same three-step pattern:
- Install the MCP server — The
blender-mcppackage (runs viauvx) - Install the Blender addon —
addon.pycreates a socket server inside Blender - Connect — Your AI client talks to the MCP server, which talks to Blender
For a technical deep dive into the architecture, see our MCP Server guide.
Get Started with Blender MCP
Blender MCP is free, open-source, and community-driven. Star the repo, report issues, or contribute — all on GitHub.
View on GitHub →