Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Openusd

БесплатноНе проверен

Enables AI assistants to read, inspect, and manipulate OpenUSD 3D scenes, including scene graph traversal, property querying, mesh export, and variant switching

GitHubEmbed

Описание

Enables AI assistants to read, inspect, and manipulate OpenUSD 3D scenes, including scene graph traversal, property querying, mesh export, and variant switching.

README

An MCP server that lets AI assistants read, inspect, and manipulate OpenUSD scenes.

Live Demo — interactive 3D viewer with variant switching

pip install openusd-mcp

What it does

Connect this MCP server to Claude, ChatGPT, Cursor, or any MCP-compatible client. Your AI assistant can then work directly with .usda, .usdc, and .usdz files — inspecting scene graphs, querying properties, exporting meshes, and switching variants.

Tools

Tool Description
usd_inspect Read the scene graph — list all prims, types, hierarchy
usd_get_prim Get detailed properties, attributes, and metadata for a specific prim
usd_get_materials List all materials and their shader parameters
usd_get_transforms Get world-space transforms for prims
usd_list_variants List all variant sets and their options
usd_set_variant Switch a variant selection
usd_export_mesh Export a mesh prim as STL or OBJ
usd_scene_stats Get scene statistics — prim count, mesh count, material count, bounding box

Quick start

With Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "openusd": {
      "command": "openusd-mcp",
      "args": []
    }
  }
}

Then try it with the included example scenes:

"Inspect the scene graph of examples/desk_setup.usda and describe what's on the desk."

"What color options does the product in examples/product_configurator.usda have? Switch it to gold."

With any MCP client

openusd-mcp --stdio

The server communicates over stdin/stdout using the MCP protocol.

Examples

The repo includes two example scenes that exercise all 8 tools.

Desk setup — scene inspection

A desk with a table, monitor, keyboard, and mug. 5 PBR materials (wood, metal, screen, ceramic, dark plastic), 10 meshes, real-world dimensions.

You: What's in examples/desk_setup.usda?

Claude: A desk scene with 25 prims, 10 meshes, 5 materials:

  /Desk (Xform)
    /Desk/Table/Top (Mesh) — Wood, 120×60×3 cm
    /Desk/Table/Leg1..4 (Mesh) — Metal
    /Desk/Monitor/Screen (Mesh) — dark glossy
    /Desk/Monitor/Stand (Mesh) — Metal
    /Desk/Monitor/Base (Mesh) — Metal
    /Desk/Keyboard (Mesh) — DarkPlastic
    /Desk/Mug/Body (Mesh) — Ceramic

  Bounds: 1200 × 835 × 1250 mm

You: Export the tabletop as STL

Claude: Exported /Desk/Table/Top to tabletop.stl (12 triangles, 684 bytes)

Product configurator — variant switching

A device with 3 variant sets: size (small, medium, large), color (midnight, silver, gold, red), and finish (matte, satin, glossy).

You: What configuration options does examples/product_configurator.usda have?

Claude: The product at /Product has 3 variant sets:

  size:   small | medium* | large
  color:  midnight* | silver | gold | red
  finish: matte | satin* | glossy

  (* = currently selected)

You: Switch to gold, large, glossy

Claude: Done. Updated /Product:
  size:   large (1.4× scale)
  color:  gold — diffuseColor: (0.83, 0.69, 0.22), metallic: 0.9
  finish: glossy — roughness: 0.1

Requirements

  • Python 3.9+
  • usd-core (Pixar's USD Python bindings)
pip install usd-core

How it works

The server uses Pixar's official pxr Python bindings (the same libraries used by NVIDIA Omniverse, Apple's Reality Composer, and every major VFX pipeline) to read and manipulate USD stages. It exposes these capabilities as MCP tools that any AI assistant can call.

OpenUSD is the industry standard for describing 3D scenes, backed by Pixar, Apple, NVIDIA, Adobe, and Autodesk. As of December 2025, the Alliance for OpenUSD has ratified Core Specification 1.0.

Author

Mirko KieferDaslab

License

MIT

Links

  • OpenUSD — Universal Scene Description
  • AOUSD — Alliance for OpenUSD
  • MCP — Model Context Protocol
  • Daslab — Where AI meets the physical world

from github.com/daslabhq/openusd-mcp

Установка Openusd

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/daslabhq/openusd-mcp

FAQ

Openusd MCP бесплатный?

Да, Openusd MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Openusd?

Нет, Openusd работает без API-ключей и переменных окружения.

Openusd — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Openusd в Claude Desktop, Claude Code или Cursor?

Открой Openusd на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Openusd with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai