cad-mcp-server
Give your AI assistant the ability to inspect, measure, and compare 3D CAD models by dropping in a STEP file and asking engineering questions. Runs entirely on your machine with no cloud, no CAD license, and no setup.
README
CAD MCP Server
Give your AI assistant the ability to inspect, measure, and compare 3D CAD models. Drop in a STEP file, ask engineering questions, get measured answers. Runs entirely on your machine — no cloud, no CAD license, no setup.
Quick Start
npx -y cad-mcp-server
Add to your MCP client:
{
"mcpServers": {
"cad": {
"command": "npx",
"args": ["-y", "cad-mcp-server"]
}
}
}
Point your AI at any STEP file and ask questions like:
"Review this part before manufacturing. Check wall thickness, draft angles, and hole sizes. Flag anything that violates standard DFM rules."
Why Engineers Use It
- Zero setup. One command. No CAD software, licenses, Docker, or cloud API.
- Runs locally. Your STEP files never leave your machine.
- Deterministic answers. Backed by the Open CASCADE kernel, not LLM guessing.
- Read-only. Inspects geometry without modifying anything.
What It Can Do
| Tool | Example question |
|---|---|
inspect_step |
"What are the overall dimensions and volume?" |
find_faces |
"Find all cylindrical faces. Which ones are holes vs bosses?" |
find_edges |
"What's the smallest fillet radius on this part?" |
measure_geometry |
"Check wall thickness around every hole. Flag anything below 2mm." |
diff_step |
"What changed between revision A and revision B?" |
The AI assistant interprets the measurements. You get engineering answers, not raw numbers.
Example Prompts
- "Review this part for injection molding: check draft angles with +Z pull, measure minimum wall thickness, identify undercuts."
- "Prepare a first-pass CNC plan: likely setups, drilling directions, features that drive cost."
- "Compare these two revisions and flag what needs rechecking before tooling."
- "Which holes are blind vs through? What's the depth of the blind hole?"
- "Find the thinnest wall section on this part. Is it above the 1.5mm minimum?"
See docs/EXAMPLE_PROMPTS.md for more.
Requirements
- Node.js 24+
- STEP files (export from SolidWorks, FreeCAD, Fusion 360, CATIA, or any CAD system)
License
MIT. The bundled OCCT kernel uses LGPL-2.1. See THIRD_PARTY_NOTICES.md.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.