The CAiD MCP Server provides validated 3D CAD modeling for AI agents using CAiD and OpenCASCADE, functioning as a server without a GUI. It ensures geometry operations are validated to prevent silent failures common in CAD operations.
From the registry: Validated 3D CAD modeling for AI agents via CAiD + OCCT. 107 tools across 22 modules.

$ pip install caid && git clone https://github.com/dreliq9/caid-mcp && cd caid-mcp && pip install -e .https://github.com/dreliq9/caid-mcpPlease install the `caid-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Create a Python venv with CAiD installed** — Create a Python venv and install caid (it pulls in OCP), then clone caid-mcp and pip install -e . Run: `pip install caid && git clone https://github.com/dreliq9/caid-mcp && cd caid-mcp && pip install -e .` (https://github.com/dreliq9/caid-mcp)
Canonical MCP server config (stdio transport):
- command: `<path-to-venv>/bin/python`
- args: ["<path-to-caid-mcp>/server.py"]
- optional environment variables:
- `CAID_OUTPUT_DIR`: Directory where generated STL output files are written (example: `<your-output-dir>`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CAID_OUTPUT_DIROverrides the default output directory for exported files.Make 3D games in Unity Engine with AI. MCP Server + Plugin for Unity Editor and Unity games.