mcpField
R
Rupa3D

Rupa3D

Local
github.com/tiranyxMedia & Design
Repository

About Rupa3D

Rupa3D is a 3D asset toolkit for AI agents and CI, combining modeling with checks against specifications. It embeds measured certificates in GLB files, and can check GLB assets without Blender.

Key features

  1. 01Check GLB files against specifications
  2. 02Embed measurement certificates in GLB
  3. 03Build exact b-rep CAD models
  4. 04Create physics-enabled three.js scenes
  5. 05Inspect topology and texture density

Use cases

  1. 01Validate a GLB asset in CI
  2. 02Review measurements attached to an asset
  3. 03Create CAD geometry and export it
  4. 04Build a physics scene for a web page

MCP support

Rupa3D runs as an MCP server and exposes 3D asset checking, CAD, scene, and modeling tools to MCP clients. Some tools work without Blender; Blender is needed for the headless Blender toolset.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "tiranyx-rupa3d": {
      "command": "npx",
      "args": [
        "-y",
        "rupa3d"
      ],
      "env": {
        "RUPA3D_BLENDER": "<RUPA3D_BLENDER>",
        "RUPA3D_RUANG": "<RUPA3D_RUANG>"
      }
    }
  }
}
Run commandnpx -y rupa3d
Environment variables to set
RUPA3D_BLENDERPath to the Blender executable. Only the Blender-backed tools need it; GLB checking, CAD and scenes run without Blender.
RUPA3D_RUANGWorkspace directory for scenes and CAD shapes. Default: ~/.rupa3d

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmrupa3d1.6.2

Tools

36

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
ruangstringNoWorkspace name; each workspace has its own adegan.blend.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.