CAiD MCP Server

Validated 3D CAD modeling for AI agents via CAiD + CadQuery. 54 tools with geometry validation.

Local serverstdioPython

What is the CAiD MCP server?

CAiD MCP server exists for a simple reason — assistants are far more useful when they can act on CAiD directly instead of describing what you should do. Validated 3D CAD modeling for AI agents via CAiD + CadQuery. 54 tools with geometry validation.

What you get

Every geometry operation is validated through CAiD's ForgeResult system, which tracks volume, surface area, and diagnostics. If a boolean silently fails (common with OCCT), the validation layer catches it and tells you why.

What the assistant can call

Once CAiD is connected, these are the calls the assistant has available:

  • Category — Count
  • primitives — 7
  • modify — 4
  • transforms — 4
  • booleans — 4
  • query — 6
  • view — 2
  • scene — 5
  • export — 5
  • heal — 3
  • assembly — 5
  • compound — 3

Setting it up

The server ships on PyPI as caid, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

You will need one environment variable: CAID_OUTPUT_DIR. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.11+

Choosing this one

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. CAiD's toolset — Category, primitives, modify and 11 more — is a fair guide to whether it matches your workflow. It is maintained by dreliq9; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against CAiD's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch CAiD.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the caid mcp server does with a few real requests.

Available tools

ToolWhat it does
CategoryCount
primitives7
modify4
transforms4
booleans4
query6
view2
scene5
export5
heal3
assembly5
compound3
advanced3
PrerequisitesThe Prerequisites tool exposed by this server.

How to install the CAiD MCP server

{
  "mcpServers": {
    "caid": {
      "command": "uvx",
      "args": ["caid"],
      "env": {
        "CAID_OUTPUT_DIR": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.11+
VariableDescriptionRequired
CAID_OUTPUT_DIRFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use CAiD to Category.
  • Use CAiD to primitives.
  • Use CAiD to modify.

Frequently asked questions

It connects CAiD to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Category, primitives, modify, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with CAiD directly.