pickfit

BrowseMCP servers

Ottogeo — CAD MCP Server

MCP server that lets AI assistants measure STEP CAD geometry using Open CASCADE.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js 24+
  1. install cad-mcp-server globally with npm

    npm install -g cad-mcp-server
Where the README and reality differ
  • README: Requirements: Node.js 24+
    What worked: works on Node v22.23.4; package.json engines allows >=22
  • README: Tools table lists inspect, find_entities, measure, describe_pmi, diff
    What worked: server exposes inspect_step, query_step, diff_step, transact_step over stdio

Add it to your agent

claude mcp add cad-mcp-server -- cad-mcp-server
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "cad-mcp-server": {
      "command": "cad-mcp-server",
      "args": []
    }
  }
}

Add the server to your MCP-capable AI assistant's configuration, then ask the assistant to inspect a STEP file.

What it does

  • Measure geometry in STEP CAD files
    Not tested
  • See part size, volume and hole diameters
    Not tested
  • List declared PMI dimensions and tolerances
    Not tested
  • Compare two STEP revisions for changes
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • get overall dimensions and volume of a STEP part
  • find cylindrical faces and list diameters and axes
  • measure wall thickness on faces
  • cut a planar section through a body
  • compare what changed between two STEP revisions

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client connects and lists its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.3.2

An MCP client handshake over stdio listed 4 tools.

Differences the test machine hit

  • README: launch via npx -y cad-mcp-server
    In the test: binary starts stdio server and waits on stdin; no --help/--version output

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.