
This is a MCP Server that allows LLM to interact with Rhino and Grasshopper directly.
This is a MCP Server that allows LLM to interact with Rhino and Grasshopper directly.
·
GH_mcp_server provides an approach that allows designer to interact with Rhino and Grasshopper directly via LLMs, including to analyse .3dm file, do 3D modeling and generate GHPython automatically in Grasshopper based on user’s guidance.
This project is still under construction — and we’d love your help!
- Feel free to open an issue if you encounter bugs or have ideas.
- Pull requests are always welcome.
- If you're interested in collaborating long-term, feel free to reach out to [email protected] — we’d love to have you on the team!
Rhino 7 or 8
Install RhinoPython: https://github.com/jingcheng-chen/RhinoPythonForVscode/tree/master?tab=readme-ov-file
uv
# For MacOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh# For Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Claude Desktop
git clone [email protected]:veoery/GH_mcp_server.git
cd GH_mcp_serverWe recommend using uv:
uv venv
source .venv/bin/activate
uv pip install -e .uv venv
.venv\Scripts\activate
uv pip install -e .Make sure the virtual environment is activated before running or developing the project.
In the Claude Desktop, Navigate to Settings->Developer. You will see Edit Config.
Click the Edit Config and open the file claude_desktop_config.json
Place the following code to the json file:
{
"mcpServers": {
"grasshopper": {
"command": "path_to_GH_mcp_server/.venv/bin/python",
"args": [
"path_to_GH_mcp_server/run_server.py"
]
}
}
}Restart the Claude Desktop. If you are able to see a hammer icon, the configuration is successful. Click the hammer icon to check all the attached MCP tools.
Start Rhino
Type command CodeListener. You should see VS Code Listener Started....
Open the Claude Desktop and type the prompts to interact with GH_mcp_server tools. Please also check the file examples\zaha01.gh as a reference for interacting with Grasshopper. Here are some examples:
Read the file "D:\test01.3dm" first and analyse the objects in this file.write GHpython to create a tower referring to zaha and write the ghpython code to "D:\zaha01.py"
This repo does not document an install step we could read. Check the README on GitHub.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/gh-mcp-server to learn what the "Gh Mcp Server" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
This server doesn't publish a machine-readable tool manifest, and it doesn't expose a public endpoint we could ask. Connect the server locally to see what it exposes.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/gh-mcp-server)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "gh-mcp-server" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.