Skip to content
MCP server

SpatialPack — 3D asset readiness

Checks whether 3D .glb files work in Apple Quick Look and Safari, then repairs and shrinks

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
Web, CLI, API
Runs
Locally
Version
0.1.0
Listing updated
today

Similar MCP servers

About SpatialPack — 3D asset readiness

SpatialPack — 3D asset readiness is a freemium MCP server for design and media. It runs locally on your machine and is started by your AI client.

The README-less product centers on a readiness verdict for glTF and GLB models across Apple Quick Look, Safari's model element and Shopify AR. Its checks flag USDZ packaging faults, metersPerUnit and up-axis mistakes, and image encoding problems that Apple's usdchecker does not report. Failing files can be passed through an autocorrect step that clears blockers and re-scores the result.

The same engine ships as a CLI, a GitHub Action and an MCP server published on npm as @spatialpack/mcp, so a check run in the browser matches what runs in code review. A 6-view visual diff with a ΔE94 threshold can fail a build when a repair changes how a model looks. Checking a file is free and needs no account, while downloading the repaired GLB requires a free sign-in.

The product suits 3D teams and e-commerce catalogs that publish models to iPhone and web storefronts. Pricing covers a free monthly download allowance, a Pro subscription and a per-model batch repair service.

Install

Run in a terminal

claude mcp add mcp -- npx -y @spatialpack/mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@spatialpack/mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@spatialpack/mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@spatialpack/mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@spatialpack/mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@spatialpack/mcp"
      ]
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Configuration

  • SPATIALPACK_MCP_SANDBOXSandbox root for asset reads and writes, equivalent to --sandbox. Defaults to a per-process temp directory.
  • SPATIALPACK_MCP_LOGLog level for the JSON-Lines diagnostic stream on stderr: debug, info, warn, error, or silent. Defaults to info.

What it does

Platform readiness verdict
Returns a ready, warnings or not-ready result for Apple Quick Look, Safari model elements and Shopify AR.
Apple-specific validation checks
Adds USDZ, PNG and JPEG checks on top of the USD spec validator to catch silent failures on iOS.
Autocorrect repair pass
Repairs blocking issues and re-scores the file before optimizing its size.
Visual diff gate
Compares six rendered views with ΔE94 and SSIM and can fail a CI build past a threshold.
Texture deduplication
Finds identical image content across glTF and USD bundles to shrink large catalogs.
MCP server integration
Exposes analyze and optimize actions to AI agents such as Claude Code and Cursor over stdio.

Good for

  • Confirm a product model opens in Quick Look before publishing a catalog to iPhone shoppers
  • Add an asset check and visual diff to a GitHub pull request that touches .glb files
  • Shrink oversized GLB files for web storefronts while reviewing the visual change
  • Let an AI coding agent analyze and optimize 3D assets through the MCP server
  • Batch-convert a product catalog into GLB and USDZ with a before-and-after report

Pricing

Freemium, from $39 a month

Free checks and 3 downloads a month; Pro $39/mo; Catalog Rescue $15 per model after 3 free

Prices change. Check spatialpack.dev before you buy.

SpatialPack — 3D asset readiness FAQ

Is the checking tool free?

Yes. Checking a file is free and needs no account, and the CLI and local MCP server are unmetered on every plan.

How many optimized downloads does the free plan allow?

Signed-in Free accounts get 3 optimized GLB downloads every month, resetting on the 1st.

What is the starting price of the Pro plan?

Pro is listed at $39 per month, billed monthly, with a 14-day trial that starts immediately and charges on day 15.

What is the upload size limit?

The public surface accepts files up to 25 MB.

Is SpatialPack — 3D asset readiness free?

SpatialPack — 3D asset readiness has a free plan, with paid plans for more usage or features. Paid plans start at $39 a month.

How do I add SpatialPack — 3D asset readiness to Claude Code?

Run this command in your terminal: claude mcp add mcp -- npx -y @spatialpack/mcp

What are the best alternatives to SpatialPack — 3D asset readiness?

The closest alternatives to SpatialPack — 3D asset readiness are Assets for three.js, 3d Texture Toolkit, 3DPACK.ING — 3D Bin Packing, Thicken and Xpensiv.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers