Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"agentcad": {
"args": [
"agentcad"
],
"command": "uvx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
CAD tool for AI agents. Give your coding agent the ability to design 3D models.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'agentcad' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked agentcad against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml
Dynamic problem-solving through sequential thought chains
Persistent memory using a knowledge graph
An autonomous agent that conducts deep research on any data using any LLM providers
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration
MCP Security Weekly
Get CVE alerts and security updates for Agentcad and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
CAD tool for AI agents. Give your coding agent the ability to design 3D models.
Your agent writes CadQuery or build123d Python scripts. agentcad handles execution, STEP export, PNG rendering, mesh export (STL/GLB/OBJ), geometric metrics, validation, diffing, and browser preview. All command output is structured JSON.
agentcad is open source under the Apache License 2.0. It runs locally and requires no signup.
A coding agent designing in agentcad, live. See more at agentcad.dev.
New: specs and measurements
agentcad measurereads the actual STEP geometry: dimensions, cylindrical feature buckets, diameters, and counts.agentcad check-speccompares the model against explicit feature requirements before the agent says it is done.agentcad view --spec spec.jsonopens a Spec check review mode so humans can inspect pass/fail results in the browser.
Install agentcad, then paste this into Claude Code, Cursor, or any coding agent:
Create a Python 3.12 virtual environment, then:
pip install agentcad
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.
agentcad run script.py --output label — execute a build123d or CadQuery script, produce versioned STEP file + geometric metrics (volume, dimensions, validity, face/edge counts)agentcad run ... --preview — four-view PNG + turntable GIF for visual verificationagentcad run ... --render iso,front — high-quality PNG viewsagentcad run ... --export stl,glb — mesh export for 3D printing or web viewersagentcad measure output.step — dimensional report (overall metrics, edge lengths, face areas, circular/cylindrical diameters)agentcad check-spec output.step spec.json — compare measured cylindrical features against an explicit checklistagentcad inspect output.step — topology deep-dive (shells, free edges, validity)agentcad diff 1 2 — compare versions (metrics, outputs, parameters)agentcad view output.step — open STEP/GLB output in a browser preview vieweragentcad docs [section] — 17 sections of built-in documentationScripts need zero imports. By default, build123d primitives, show_object, and agentcad edit helpers are pre-injected:
box = Box(10, 20, 5)
show_object(box)
CadQuery remains supported via import cadquery as cq, agentcad init --runtime cadquery, or agentcad run --runtime cadquery. Run agentcad docs runtimes for the dispatch rules.
For native tool integration with Claude Code, Cursor, or Windsurf:
pip install agentcad[mcp]
Add to .mcp.json:
{"agentcad": {"command": "python", "args": ["-m", "agentcad.mcp"]}}
Apache License 2.0. See LICENSE.
If your agent struggles, run agentcad feedback "what happened" to capture a friction log.