The Grasshopper MCP Bridge serves as a connection point between Grasshopper and Claude Desktop, using the Model Context Protocol (MCP) standard. This bridge allows you to control Grasshopper through natural language commands, with features like intent recognition and component pattern creation.
Method 1: Download pre-compiled component (Recommended)
%APPDATA%\Grasshopper\Libraries\
Method 2: Build from source
If you prefer building from source, clone the repository and build the C# project using Visual Studio.
Method 1: Install from PyPI (Recommended)
pip install grasshopper-mcp
Method 2: Install from GitHub
pip install git+https://github.com/alfredatnycu/grasshopper-mcp.git
Method 3: Install from Source Code
git clone https://github.com/alfredatnycu/grasshopper-mcp.git
cd grasshopper-mcp
pip install -e .
Install a Specific Version
pip install grasshopper-mcp==0.1.0
Or from a specific GitHub tag:
pip install git+https://github.com/alfredatnycu/[email protected]
Start Rhino and Grasshopper Launch Rhino and open Grasshopper.
Add the GH_MCP Component to Your Canvas Find the GH_MCP component in the Grasshopper component panel and add it to your canvas.
Start the Python MCP Bridge Server Open a terminal and run:
python -m grasshopper_mcp.bridge
Note: The grasshopper-mcp
command might not work directly due to Python script path issues. Using python -m grasshopper_mcp.bridge
is more reliable.
Connect Claude Desktop to the MCP Bridge
Method 1: Manual Connection In Claude Desktop, connect to the MCP Bridge server using:
Method 2: Auto-Start Configuration Configure Claude Desktop to automatically start the MCP Bridge server:
"grasshopper": {
"command": "python",
"args": ["-m", "grasshopper_mcp.bridge"]
}
Start Using Grasshopper with Claude Desktop You can now control Grasshopper through natural language commands in Claude Desktop.
You can use commands like:
grasshopper-mcp
command doesn't work, use python -m grasshopper_mcp.bridge
insteadThere 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.
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"
]
}
}
}
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.
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.