Rhino 3D MCP server

The Rhino MCP Server enables AI assistants like Claude to interact with Rhino 3D software, allowing for the creation and manipulation of 3D objects directly through the Model Context Protocol (MCP).

Installation

Prerequisites

1. Rhino 3D software
2. Claude Desktop application
3. Python environment

Setup Process

1. Configure Claude Desktop

1. Install Claude Desktop if you haven't already
2. Go to Claude Desktop settings and configure the MCP server connection

2. Run the MCP Server

The unified server launcher provides multiple ways to run the server:

./server_launcher.sh [mode]

The most common modes are:

• combined (default) - Recommended server implementation
• direct - Run both daemon and socket proxy
• standalone - Run the standalone server

For example, to run the recommended combined server:

./server_launcher.sh

Or to use the socket-based approach:

./server_launcher.sh direct

Usage

Available Modeling Tools

The MCP server provides several tools for 3D modeling operations:

Geometry Creation

• Create a sphere:

  geometry_tools.create_sphere
  

• Create a box:

  geometry_tools.create_box
  

• Create a cylinder:

  geometry_tools.create_cylinder
  

Scene Management

• Get scene information:

  scene_tools.get_scene_info
  

• Clear objects from scene:

  scene_tools.clear_scene
  

• Create a new layer:

  scene_tools.create_layer
  

Example Usage Flow

1. Start the MCP server using the launcher
2. Open Claude Desktop and connect to the server
3. Use Claude to send commands to Rhino, for example:
   • "Create a sphere with radius 5 at the origin"
   • "Create a box with dimensions 2x3x4"
   • "Clear all objects from the scene"

Troubleshooting

Connection Issues

If you experience connection problems:

1. Clean up existing processes:

   ./server_launcher.sh help
   

2. Check log files for errors:

   ./server_launcher.sh logs   # View general logs
   ./server_launcher.sh errors # View only errors
   

3. Monitor logs in real-time:

   ./server_launcher.sh monitor
   

4. Restart Claude Desktop completely

Advanced Diagnostics

For more detailed troubleshooting:

• Test Rhino connection:

  python diagnose_rhino_connection.py
  

• Generate error reports:

  ./log_manager.py report
  

All logs are stored in the logs/ directory with separate subdirectories for each component.

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.