lucad
Click on "Deploy 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., "@lucadDesign a mounting bracket with four bolt holes 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.
lucad
Agent-assisted CAD engineering: deterministic engine + thin MCP. The engine has zero LLM runtime dependency (DEC-002 / NFR-001).
Install
curl -fsSL "https://raw.githubusercontent.com/Ngoctrong102/lucad/main/install.sh" | bashFrom a clone (editable, same isolated venv — not a project .venv):
./install.shlucad upgrade # later: pull latest into the CLI venv
lucad uninstall # remove the CLI (this checkout stays)Related MCP server: Greenloom CAD MCP Server
Use
cd your-project # host machine/job (any name); not the CLI venv
lucad init # or: lucad init /path/to/hostThat’s it — host folders (drawings/, artifacts/handoff, artifacts/preview, plan/, .lucad/) plus .cursor/mcp.json. Does not create a project .venv.
Restart Cursor (Developer: Reload Window). Settings → MCP → lucad-cad should be green.
Then in Agent chat: design brief → plan/ notebook → gates → cad_execute → cad_validate → cad_export.
Layout
your-project/
plan/ ← engineering notebook (many YAML files; commit this)
drawings/ ← live FreeCAD
artifacts/handoff/ ← STEP
artifacts/preview/ ← STL/GLB
.lucad/ ← ledger (engine only)
parts/ assemblies/ ← kit templates
.cursor/mcp.jsonDocs
This server cannot be deployed
Maintenance
Related MCP Connectors
- OwlCADOAuthcom.owlcad
Parametric 3D CAD for AI agents: build print-ready parts, check them, export STL, 3MF or STEP.
1 Agent-first CAD: editable .kcad.ts source, deterministic review, OpenCASCADE kernel.
Design domain models and generate deterministic multi-stack code, driven by your coding agent.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Related MCP Servers
- AlicenseBqualityCmaintenanceConnects AI coding agents to Autodesk Fusion 360 for CAD automation, enabling natural language control over sketching, 3D modeling, and CAM operations. It uses a Python-based bridge and a custom add-in to execute over 80 tools ranging from simple geometry creation to complex assembly and parameter management.80341 PyPI91MIT
- AlicenseAqualityDmaintenanceEnables automated CAD operations via natural language, supporting both AutoCAD LT on Windows and headless DXF generation on any platform.8MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to safely generate parametric CAD parts (STEP/STL) using verified templates and FreeCAD, with validation and assembly support.MIT
- AlicenseNot gradedqualityAmaintenanceEnables coding agents to convert natural language engineering prompts into editable parametric CAD models with deterministic parsing, validation, and edit support.6Apache 2.0