Blender MCP Senpai

Blender MCP Senpai is your AI-assisted mentor for Blender that helps you spot topology issues and get real-time improvement tips directly in your workflow. It runs locally or via a lightweight MCP server, so you can enable guided feedback without heavy setup.

How to use

You use Blender MCP Senpai by connecting your Blender add-on client to an MCP server. Once connected, you get instant topology hints (like n-gons) and AI-driven comments offering improvement suggestions. The setup is designed to be zero-configuration for the client, so you can start analyzing models right away after the initial enablement.

In practice, you enable the extension in Blender, then configure the MCP server connection in your client. You can run the server locally or point to a remote endpoint. When your client is connected, topological issues are highlighted in real time and the AI can propose concrete changes you can apply in your modeling workflow.

How to install

Prerequisites: ensure you have Blender installed and a compatible MCP client feature ready to connect to an MCP server. You may also need Node.js and npm if you plan to run a local MCP server or use npx-based commands.

Step 1: Install the Blender Senpai extension for Blender

• Open Blender
• Go to Edit > Preferences > Get Extensions > Repositories > +
• Add Remote Repository: https://xhiroga.github.io/blender-mcp-senpai/extensions/index.json
• Search for Blender Senpai and install it
• Enable the Blender Senpai add-on under Add-ons

Step 2: Configure the MCP server connection in your client You can connect using a local MCP server or a remote endpoint. The following configurations show how to run a local server and connect your client to it.

{
  "mcpServers": {
    "blender_senpai": {
      "command": "npx",
      "args": [
        "-y",
        "supergateway",
        "--sse",
        "http://localhost:13180/sse"
      ]
    }
  }
}

How to run the local MCP server and connect

If you prefer running the server locally, you can use the provided command to start the gateway that serves the MCP events via SSE. After starting, ensure your client is configured to point to the local SSE endpoint.

{
  "mcpServers": {
    "blender_senpai": {
      "transport": "sse",
      "enabled": true,
      "command": null,
      "args": [],
      "env": {},
      "url": "http://localhost:13180/sse"
    }
  }
}

Notes on configuration and usage

• After configuring, restart the application if required to apply changes, especially on Windows where you may need to terminate and restart processes.

• If you run into issues connecting, verify that the SSE URL is reachable and that the MCP server process is running. Check any firewall or security software that might block the local port.

Available tools

Auto n-gon Highlight

Automatically detects and highlights n-gons and topology issues so you can address problematic areas quickly.

AI Comments

Offers real-time improvement suggestions powered by AI models like ChatGPT, Claude, and Gemini to guide your modeling workflow.

Zero Configuration

Works out-of-the-box with no external MCP client setup required for most Blender workflows.