asmith26/jupytercad-mcp

jupytercad-mcp

An MCP server for JupyterCAD that allows you to control it using LLMs/natural language.

https://github.com/user-attachments/assets/7edb31b2-2c80-4096-9d9c-048ae27c54e7

Suggestions and contributions are very welcome.

Usage

The default transport mechanism is stdio. To start the server with stdio, use the following command:

To use the streamable-http transport, use this command instead:

Example

An example using the OpenAI Agents SDK is available at examples/openai_agents_client.py. To run it, follow these steps:

1. Clone the repository and navigate into the directory:

   git clone git@github.com:asmith26/jupytercad-mcp.git
   cd jupytercad-mcp
   

2. Install the OpenAI Agents SDK. A Makefile target is provided for convenience:

   make setup-examples-env
   

3. In examples/openai_agents_client.py, update line 13 to configure a MODEL (see supported models).

4. Run JupyterLab from the project's root directory:

   make jupyter-lab
   

5. In JupyterLab, create a new "CAD file" and rename it to my_cad_design.jcad. This file path matches the default JCAD_PATH in the example, allowing you to visualise the changes made by the JupyterCAD MCP server.

6. (Optional) The OpenAI Agents SDK supports tracing to record events like LLM generations and tool calls. To enable it, set USE_MLFLOW_TRACING=True and run the MLflow UI:

   make mlflow-ui
   

7. Run the example with the default instruction, "Add a box with width/height/depth 1":

   make example-openai-agents-client