Jupytercad MCP

Communauté Autres

Control JupyterCAD using natural language.

Que pouvez-vous faire avec Jupytercad MCP ?

  • get_current_cad_design: Reads the current content of the JCAD document.
  • remove: Remove an object from the document.
  • rename: Rename an object in the document.
  • add_annotation: Add an annotation to the document.
  • remove_annotation: Remove an annotation from the document.
  • add_occ_shape: Add an OpenCascade TopoDS shape to the document.
  • add_box: Add a box to the document.
  • add_cone: Add a cone to the document.

Installation

Les étapes d'installation sont dans la documentation ci-dessous. Documentation

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

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:

uvx --with jupytercad-mcp jupytercad-mcp

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

uvx --with jupytercad-mcp jupytercad-mcp streamable-http
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
Interactive Chat Interface

The example includes an interactive chat interface using the OpenAI Agents SDK's REPL utility. To enable it, set USE_REPL=True.

streamable-http

To use the streamable-http transport, first start the MCP server:

uvx --with jupytercad-mcp jupytercad-mcp streamable-http

Then, run the example with the TRANSPORT variable set to "streamable-http" in the client example.

Tools

The following tools are available:

  • get_current_cad_design: Reads the current content of the JCAD document.
  • remove: Remove an object from the document.
  • rename: Rename an object in the document.
  • add_annotation: Add an annotation to the document.
  • remove_annotation: Remove an annotation from the document.
  • add_occ_shape: Add an OpenCascade TopoDS shape to the document.
  • add_box: Add a box to the document.
  • add_cone: Add a cone to the document.
  • add_cylinder: Add a cylinder to the document.
  • add_sphere: Add a sphere to the document.
  • add_torus: Add a torus to the document.
  • cut: Apply a cut boolean operation between two objects.
  • fuse: Apply a union boolean operation between two objects.
  • intersect: Apply an intersection boolean operation between two objects.
  • chamfer: Apply a chamfer operation on an object.
  • fillet: Apply a fillet operation on an object.
  • set_visible: Sets the visibility of an object.
  • set_color: Sets the color of an object.

Questions fréquentes

Qu'est-ce que Jupytercad MCP ?

Control JupyterCAD using natural language.

Comment installer Jupytercad MCP ?

Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.

Jupytercad MCP est-il open source ?

Oui. Son code est sur GitHub sous licence Apache-2.0.

Qui maintient Jupytercad MCP ?

Il est publié par asmith26. AI.tn le référence sans le maintenir ni le recommander.

Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.