Scripted CAD execution
Runs scripts and returns versioned STEP files together with geometric metrics so the agent can verify dimensions and validity after each attempt.
agentcad
agentcad is an open-source CAD tool for AI agents that lets coding agents design, render, validate, and export real CAD output. It runs locally and supports scripted workflows through a CLI and MCP server.
Overview
agentcad is an open-source CAD tool for AI agents. It gives coding agents a way to design, render, validate, and export real CAD output instead of stopping at code or approximations.
The site presents it as a local workflow for human-agent collaboration: the agent runs a CAD script, reads back metrics and renders, corrects mistakes, and iterates until the geometry is valid and ready to hand off. The public site highlights STEP, STL, GLB, and OBJ output, plus previews, validation, and version diffs.
Core capabilities
Rendered previews
Generates PNG previews from different angles so the agent can inspect the model visually before handing it off.
Multi-format export
Exports common downstream formats including STL, GLB, and OBJ for printing, viewers, or further processing.
Validation before run
Performs pre-execution checks that can catch errors quickly, helping the agent avoid continuing with invalid geometry.
Debugging and iteration tools
Provides topology reports and version diffs so changes between iterations are easier to debug and compare.
CLI and MCP access
Supports both CLI use and MCP integration for agent tooling, with install examples for local and cached execution paths.
Common use cases
Iterative agent-driven CAD
A coding agent writes a CAD script, runs it locally, checks the returned metrics and renders, and revises the model until the geometry matches the brief.
Agent tool integration
A developer uses the CLI or MCP server inside a coding environment such as Claude Code, Cursor, or Windsurf to add CAD generation to an agent workflow.
3D model export and handoff
A user needs inspectable 3D output for printing or sharing, so the agent exports STEP, STL, or GLB after validation passes.
Design iteration review
A builder wants to compare successive versions of a part or assembly and uses the rendered previews, metrics, and diffs to see what changed.
Pros and Cons
Pros
- Open source and runs locally, which fits agent workflows that need direct access to files and outputs.
- Produces both visual previews and machine-readable metrics, giving agents more than one way to verify geometry.
- Supports common export formats for printing and web/viewer workflows.
- Includes version diffs and topology reporting that support iterative debugging.
- Provides both CLI and MCP integration paths, so it can be used in more than one agent setup.
Cons
- The public site does not provide a complete feature matrix or documented plan comparison.
- The pricing page in the supplied snapshot returns a 404, so pricing details are not available from the site content provided.
- The site frames agentcad around scripted, agent-driven CAD workflows rather than a traditional interactive CAD editor.
FAQ
How do you set it up?
agentcad runs locally as an open-source CLI and MCP server. The install examples on the site show Python 3.10–3.12 support and a package install path for `agentcad[mcp]`.
What outputs does it generate?
agentcad produces CAD outputs such as STEP, STL, GLB, and OBJ, along with PNG renders and validation metrics so an agent can inspect geometry before handoff.
How is it meant to be used in a workflow?
The site positions agentcad for human-agent collaboration on CAD tasks: an agent runs scripts, reads metrics and renders, and then iterates until the geometry is valid or matches the specification.
What are the main limitations or fit notes?
The source describes pre-execution validation, metrics, renders, and version diffs, but it does not document every possible limitation. It is intended for code-driven CAD workflows rather than a standalone visual CAD editor.
Is there pricing information on the site?
The pricing page at `/pricing` currently returns a 404 on the site snapshot, so the public site does not provide a pricing table or plan details to extract.
Quick Facts
- Category
- Developer Tool
- Primary use
- AI-assisted CAD generation and verification
- Delivery
- Open-source CLI and MCP server
- Supported Python
- 3.10–3.12
- Source domain
- agentcad.dev
- License
- Apache-2.0 (source repository)
agentcad Alternativen
DeepMotion
DeepMotion is a web-based AI motion capture and 3D animation platform with Animate 3D for video-to-animation and SayMotion for text-to-animation. It helps creators and teams generate motion in a browser and export results in common production formats.
图像大厨imgcook
imgcook is a design-to-code tool that converts design drafts into front-end code. It supports plugin-based and developer workflows for Sketch, Photoshop, VS Code, and CLI usage.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Ably Chat
Ably Chat is a chat API platform for building custom realtime chat applications. It supports room-based messaging, typing indicators, presence, reactions, and message updates, with usage-based pricing options for different deployment stages.