ai-cad-workbench
Provides integration with AutoCAD for CAD model building, inspection, and rendering workflows.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ai-cad-workbenchBuild the mounting_plate model and export as STEP"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI CAD Workbench
面向 AI Agent 的 Python CAD 执行层。AI 负责理解需求和修改参数化源码;本工具负责受控构建、STEP/DXF/GLB 导出、检查、渲染、差异比较与证据记录。
它不是“输入一句话就自动保证可制造”的黑盒。工程图、材料、公差、工艺和签审仍需由具备资质的工程人员确认。
能力
model.py + model.cad.json源码式参数化建模build123d/OCP 三维内核与 ezdxf 二维图纸
STEP、GLB、DXF、PNG、拓扑 JSON 和统一 Pydantic 报告
doctor / describe / build / inspect / measure / diff / render / reviewPython SDK、CLI、MCP 三套一致接口
Web Studio:独立三维装配页和二维 CAD 绘制页;真实 GLB、DXF 点图切模块、逐文字编辑、毫米选区和整图重绘计划
二维模板库:内置 A3/A4 毫米制基底,支持导入企业 DXF 图框/标题栏并按内容哈希追加保存
追加式 run、输入哈希、源码快照和视觉审查记录
Related MCP server: build123d-mcp
安装
需要 Python 3.12 和 uv。
git clone --recurse-submodules https://github.com/redmaplewww/ai-cad-workbench.git
cd ai-cad-workbench
uv sync --extra dev
uv run aicad doctor --workspace . --json如果普通 clone 时没有拉子模块:
git submodule update --init --depth 1快速体验
先构建一个带孔安装板:
uv run aicad build examples/ai_cad/mounting_plate/model.cad.json --workspace . --json再启动 CAD 绘制与 AI 修改前端:
uv run aicad studio --workspace . --host 127.0.0.1 --port 8766打开 http://127.0.0.1:8766/ 查看三维装配,打开 http://127.0.0.1:8766/drawing 进入二维 CAD 绘制工作台。二维图在绘制结果建立时同步模块化;单击图元会切换到最具体模块,Shift/Ctrl 多选可建立人工编辑模块。模块只负责定位修改意图,外部 AI 始终修改完整 Python 真源并重绘整张图,再对未涉及模块执行差异校核。
Text-to-CAD 与 Skills
本仓库将 earthtojake/text-to-cad 固定为 Git 子模块,同时直接提供本项目常用 Skill:
skills/ai-cad-workbench:本工具的模型、构建、检查和 Studio 工作流skills/cad:STEP-first 参数化 CADskills/dxf:二维 DXF 与工程图skills/cad-viewer:CAD 文件可视化检查skills/pdf:PDF 阅读、渲染和版式核验
project-to-act 仅用于开发过程账本管理;因本地安装副本没有独立再分发许可证,本仓库没有复制其文件。
示例边界
公开版只保留原创、通用、可复现的示例。客户 PDF 复现图、第三方参考 STEP、许可未闭合的数据集、运行缓存和历史产物均未进入本仓库。示例图纸标注和自动检查可作为工程工作的起点,但不构成制造放行。
测试
uv run pytest
cd integrations/autocad-mcp
uv sync
uv run pytest更多说明见 docs/AI_CAD_MVP.md、docs/AI_CAD_STUDIO.md、docs/AI_CAD_CAPABILITY_INVENTORY.md 和 docs/GB_DRAWING_RULES.md。
License
本项目原创代码采用 MIT License。第三方组件与 Skills 的许可证见 THIRD_PARTY_NOTICES.md 及其目录内许可证文件。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceMCP server that exposes CAD geometry reasoning over STEP files to LLMs, allowing natural language queries about parts, assemblies, dimensions, holes, and mass properties.
- AlicenseAqualityAmaintenanceMCP server for Python build123d to help AIs develop and reason about 3D models and CAD3868Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server enabling CAD interaction with Creo Parametric and knowledge base retrieval from Volcengine.6MIT
- AlicenseBqualityAmaintenanceMCP server that lets AI draw in AutoLISP-capable CAD (reference BricsCAD on Linux) via a file bridge, enabling 2D drafting, 3D solid modeling, and verification with 100 tools.1281Apache 2.0
Related MCP Connectors
MCP server for Wan AI video generation
MCP server for AI access to Swagger by SmartBear.
MCP server for ByteDance Seedream AI image generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/redmaplewww/ai-cad-workbench'
If you have feedback or need assistance with the MCP directory API, please join our Discord server