ai-cad-workbench
MCP server for AI-driven CAD operations, enabling parametric modeling, build, inspection, measurement, rendering, and diff comparison with STEP, DXF, and GLB export.
README
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 / review- Python SDK、CLI、MCP 三套一致接口
- Web Studio:真实 GLB 三维视口、DXF 二维视口、组件/参数/提示词绑定和装配影响范围
- 追加式 run、输入哈希、源码快照和视觉审查记录
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
再启动可视化与局部提示词编辑前端:
uv run aicad studio --workspace . --host 127.0.0.1 --port 8766
打开 http://127.0.0.1:8766/。Studio 的修改请求不会直接覆盖模型,而是生成带组件范围、参数变化、空间关系和验证要求的 scoped prompt,供外部 AI Agent 修改源码后全局重建。
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 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。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.