Enterprise DNA
M MCP Servers Developer low

asmith26/jupytercad-mcp

by Various

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

A

MCP

asmith26/jupytercad-mcp

Added 1 June 2026

#cad #computer-aided-design #jupytercad #jupyterlab #mcp

Overview

asmith26/jupytercad-mcp is an MCP server that enables natural language control of JupyterCAD through large language models. It acts as a bridge between LLMs and JupyterCAD, allowing users to issue CAD commands via conversational prompts.

Best for

Best for
Developers exploring LLM-controlled CAD workflows in Jupyter environments

Use cases

  • Controlling JupyterCAD operations through natural language chat
  • Automating repetitive design steps with LLM-driven instructions
  • Integrating LLM-based assistants into JupyterCAD workflows

Notes

asmith26/jupytercad-mcp is an MCP server that enables natural language control of JupyterCAD through large language models. It acts as a bridge between LLMs and JupyterCAD, allowing users to issue CAD commands via conversational prompts.

18 stars on GitHub. Last updated 2025-10-07. Licensed Apache-2.0.

Use cases

  • Controlling JupyterCAD operations through natural language chat
  • Automating repetitive design steps with LLM-driven instructions
  • Integrating LLM-based assistants into JupyterCAD workflows

Pros

  • Open source and written in Python, easy to inspect and extend
  • Directly integrates with JupyterCAD for a seamless experience
  • Enables novel interaction patterns for CAD design

Cons

  • Low star count (18) suggests limited community adoption and testing
  • Early-stage project with potentially incomplete or unstable features
  • Dependence on external LLMs adds latency and cost

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Open source and written in Python, easy to inspect and extend
  • Directly integrates with JupyterCAD for a seamless experience
  • Enables novel interaction patterns for CAD design

Cons

  • Low star count (18) suggests limited community adoption and testing
  • Early-stage project with potentially incomplete or unstable features
  • Dependence on external LLMs adds latency and cost