Skip to main content

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

Project description

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.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jupytercad_mcp-0.1.1a2.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

jupytercad_mcp-0.1.1a2-py3-none-any.whl (4.7 kB view details)

Uploaded Python 3

File details

Details for the file jupytercad_mcp-0.1.1a2.tar.gz.

File metadata

  • Download URL: jupytercad_mcp-0.1.1a2.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for jupytercad_mcp-0.1.1a2.tar.gz
Algorithm Hash digest
SHA256 e8aef11777e61df452f11e675139c81fdfd461ea0909a6e5ec2b5811e98ba2c6
MD5 38fc4cce5a4a319aa5e06b6fcd7537d3
BLAKE2b-256 ddb2452415dd77890f2d4f4c4f2c0b41df04a2ebae3348b0b67da3e294acbe07

See more details on using hashes here.

Provenance

The following attestation bundles were made for jupytercad_mcp-0.1.1a2.tar.gz:

Publisher: publish.yaml on asmith26/jupytercad-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file jupytercad_mcp-0.1.1a2-py3-none-any.whl.

File metadata

File hashes

Hashes for jupytercad_mcp-0.1.1a2-py3-none-any.whl
Algorithm Hash digest
SHA256 e0b6934f72371ccc8a8c7745bb6838028ac2633fad98d200b897945b2308062a
MD5 9419b94f323d3c571469123baea580fd
BLAKE2b-256 5e6a8d738f95661a5f0b770c47b5f0d87a6b53c4557e4be2f17fbf9e0d0a64c0

See more details on using hashes here.

Provenance

The following attestation bundles were made for jupytercad_mcp-0.1.1a2-py3-none-any.whl:

Publisher: publish.yaml on asmith26/jupytercad-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page