agentcad

Hand off CAD to your agent.

An MCP server and CLI that lets your coding agent design, render, and export 3D models.

Free · No signup · Runs locally

Install

uv tool install 'agentcad[mcp]'

uv picks a compatible Python (3.10–3.12) automatically. CadQuery/OpenCascade does not support 3.13+.

CLI-only (no MCP server): uv tool install agentcad

No uv? Install it with brew install uv or see docs.astral.sh/uv.

See it in action

Watch one Claude session build the 1903 Wright Flyer end to end.

3D render of the 1903 Wright Flyer reconstructed in CAD — a 234-part biplane with fabric covering, twin pusher propellers, forward elevator, and twin rudders, viewed at an isometric angle

Case study · 2026

234 parts. Built with prompts.

A 3D reconstruction of the 1903 Wright Flyer, faithful to the Christman measured drawings, written in Python with agentcad.

See it in action →

Made with agentcad

Each of these was designed by an AI agent using a single prompt.

3D render of a two-piece rectangular box with filleted vertical edges and a snap-fit lid with alignment lip, light gray on dark background, approximately 64x44x46mm overall

30 faces, 72 edges, 39cm³ volume, valid geometry

3D render of a hollow revolved vase with a wide base, narrow waist, flared body, and lipped rim, dark gray on dark background, approximately 60x60x128mm

15 faces, 28 edges, 107cm³ volume, valid geometry

3D render of a chess rook with a stepped circular base, hourglass-tapered shaft, and crenellated crown with four battlements, light gray on dark background, approximately 30x30x64mm

59 faces, 140 edges, 19.2cm³ volume, valid geometry

3D render of a phone stand with flat base, vertical back support, and small front lip, light gray on dark background, approximately 80x50x69mm

10 faces, 24 edges, 42cm³ volume, valid geometry

How it works

What the agent sees, runs, and hands back.

{
  "command": "run",
  "status":  "success",
  "metrics": {
    "dimensions": {
      "x": 6480.8,
      "y": 12293.6,
      "z": 1999.9
    },
    "volume":     305738441.28,
    "face_count": 684,
    "is_valid":   true
  }
}
Agent view: four-pane preview rendered by agentcad on every successful run — TOP, ISO FRONT-RIGHT, ISO BACK-RIGHT, ISO BACK-LEFT — showing the airframe in wireframe from four angles

How it works

Designed for human–agent collaboration.

Every run returns metrics and a render. The agent reads both — and catches its own mistakes before they reach you.

See the loop →

What it does

Agents write bad geometry on the first try. agentcad gives them a tight feedback loop — run, render, inspect, fix — so they converge on printable geometry without you babysitting.

Execute
— run scripts, produce versioned STEP files + geometric metrics
Render
— PNG views from any angle for visual verification
Export
— STL, GLB, OBJ for 3D printing and web viewers
Validate
— pre-execution checks catch errors in <100ms
Inspect
— topology report for debugging geometry issues
Diff
— compare versions to track design iteration

Try it

Install agentcad, then paste this prompt into Claude Code, Cursor, or any coding agent:

Create a Python 3.12 virtual environment, then:

pip install agentcad[mcp]
agentcad skill install
agentcad --help

Read the --help output — it's your operational briefing.

Then design me a phone stand: a simple angled cradle
that holds a phone at 60 degrees. About 80mm wide,
50mm deep, with a 5mm lip at the bottom to keep the
phone from sliding. Show me a preview when you're done.

No boilerplate

Scripts need zero imports. cq, show_object, and 16 geometry helpers are pre-injected:

box = cq.Workplane('XY').box(10, 20, 5)
show_object(box)

MCP integration

Add to .mcp.json for Claude Code, Cursor, or Windsurf. Works without a prior install — uvx caches the environment on first run:

{
  "agentcad": {
    "command": "uvx",
    "args": ["--from", "agentcad[mcp]", "python", "-m", "agentcad.mcp"]
  }
}

Agent skill

agentcad is an installable agent skill on skills.sh (Vercel) and ClawHub (OpenClaw):

skills.sh (Vercel)

npx skills add jdilla1277/agentcad-skill

ClawHub (OpenClaw)

clawhub install jdilla1277/agentcad

Listing: clawhub.ai/jdilla1277/agentcad · Manifest: github.com/jdilla1277/agentcad-skill

Get release updates

Optional. New releases and agent-facing features. We’ll send a confirmation link before adding you.