Rhino 8 MCP server

RhinoMCP enables AI agents to directly interact with and control Rhino 3D through the Model Context Protocol (MCP). This integration creates a seamless connection between AI systems and Rhino, allowing for prompt-assisted 3D modeling with two-way communication.

Overview

RhinoMCP provides several key capabilities:

• Two-way communication between AI agents and Rhino
• Object creation, modification, and deletion
• Document inspection and information retrieval
• Python script execution in Rhino
• Object selection with filtering options
• Layer management (create, delete, modify)

Currently supports primitive objects like Point, Line, Polyline, Curve, Box, and Sphere, with more geometries planned for future updates.

Installation

Prerequisites

• Rhino 7 or newer (Windows or Mac) - ensure it's updated
• Python 3.10 or newer
• uv package manager

Installing the Rhino Plugin

1. Go to Tools > Package Manager
2. Search for rhinomcp
3. Click Install

Installing uv Package Manager

For Mac:

brew install uv

For Windows:

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Configuration Setup

Create a config file with the following content:

{
  "mcpServers": {
    "rhino": {
      "command": "uvx",
      "args": ["rhinomcp"]
    }
  }
}

Claude for Desktop Integration

1. Go to Claude > Settings > Developer > Edit Config
2. Update the claude_desktop_config.json to include the config above

Cursor Integration

1. Create a .cursor folder in your project root
2. Create a file called mcp.json in the .cursor folder with the config content above
3. Go to Cursor Settings > MCP and verify it's enabled

Usage

Starting the Connection

1. In Rhino, type mcpstart in the command line
2. Confirm the MCP server is running in the Rhino terminal

Using with Claude

Once properly configured, you'll see a hammer icon with tools for RhinoMCP in Claude's interface. Click this to access RhinoMCP functionality.

Using with Cursor

After configuration and with the plugin running in Rhino:

1. Look for the green indicator in front of the MCP server
2. If not visible, try refreshing the server in Cursor
3. Use Ctrl+I to open the chat box
4. Ensure you've selected Agent mode
5. Start chatting with Rhino through the AI interface

Technical Details

The communication uses a JSON-based protocol over TCP sockets:

• Commands are sent as JSON objects with a type and optional params
• Responses are JSON objects with a status and result or message

Limitations

• Document information retrieval is limited to 30 objects, layers, materials, etc. to prevent overwhelming the AI system
• Complex operations may need to be broken down into smaller steps
• Only one instance of the MCP server should run at a time (either on Cursor or Claude Desktop, not both)

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.