Drop SpatialPack into your editor.
29 tools — commerce-readiness, autocorrect, batch-autocorrect, USDZ export/validate, analyze, optimize, recipe-search, dedup, cohort recipes, LOD bundles — exposed over Model Context Protocol. Works with Claude Code, Cursor, Claude Desktop, and Continue.dev. One npx command, no install.
Copy. Paste. Done.
# One command. Nothing to clone or build.
claude mcp add spatialpack -- npx -y @spatialpack/mcp
# Verify it registered:
claude mcp list
# Then, in any session:
# "Run commerce_readiness on ./hero.glb"// ~/.cursor/mcp.json
{
"mcpServers": {
"spatialpack": {
"command": "npx",
"args": ["-y", "@spatialpack/mcp"]
}
}
}// macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
// Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"spatialpack": {
"command": "npx",
"args": ["-y", "@spatialpack/mcp"]
}
}
}# ~/.continue/config.yaml
mcpServers:
- name: spatialpack
command: npx
args:
- "-y"
- "@spatialpack/mcp"No clone, no build, no API key, no account. Run the CLI and the MCP server locally, over stdio, and every tool is free and unmetered — no key, no account, no quota. Quotas and API keys apply only to the hosted surfaces: the web app and the hosted API (including the MCP Streamable-HTTP transport). That includes optimize, autocorrect and usdz_export — all the compute happens on your machine. Also listed in the official MCP Registry as dev.spatialpack/mcp.
Same code, served over Streamable HTTP. When DATABASE_URL points at the same Postgres as the dashboard, every spatialpack login key is a valid Bearer token.
# Self-host the HTTP transport (e.g. for shared team use).
# When DATABASE_URL points at the same Postgres that backs the
# web dashboard, every `spatialpack login`-generated key is
# accepted as a Bearer token.
# The HTTP transport is a separate binary, so `-p` selects it.
DATABASE_URL=postgresql://... \
npx -y -p @spatialpack/mcp spatialpack-mcp-http \
--port 3037 --host 0.0.0.0
# Then any MCP client can point at:
# http://your-host:3037
# with header: Authorization: Bearer spk_live_...Personal API keys.
- step 01 · Sign in at spatialpack.dev/signin (free, no card).
- step 02 · On the dashboard, open the [02] API KEYS card and click Generate API key. Copy it — shown once.
- step 03 · Save it for calls to the hosted API:
npm i -g @spatialpack/cli && spatialpack login. Optional — local CLI commands never need it.
A key is only needed to call the hosted API (api.spatialpack.dev, and the MCP HTTP transport). Thehosted free tier is 3 optimized GLB downloads every month, shared with the web app; read-only tools (analyze, find_similar_assets, list_presets) are always free, and Pro is unlimited. Keys are revocable from the dashboard at any time. Running the CLI or the MCP server locally needs no key and consumes no quota.
First prompt.
Optimize the .glb at /path/to/asset.glb with the
web-mobile preset, then run safety_gate against the
result with bytesBudget=500_000 and deltaE94Max=2.0.
If the gate passes, give me the output path. If it
fails, run recipe_search and try again.The model picks the right tools, chains them, and reports the outcome. safety_gate + recipe_search together form a self-tuning loop.
This .glb came out of an AI 3D generator. Run
commerce_readiness on it. If it's not ready, run
autocorrect and show me which blockers were resolved.
Then export a USDZ with usdz_export and validate it,
so I can ship it to AR Quick Look.The AI-3D shipping loop: commerce_readiness → autocorrect → usdz_export → usdz_validate — raw generator output to AR-ready, one prompt.
All 29 tools.
analyzeFull glTF/GLB report — vertex/triangle/texture/animation counts, cohort tags, extensions, GPU memory, compatibility rollup.diagnose_assetActionable recommendations with suggested_args the model can chain straight into optimize.compatibility_checkPer-target compatibility matrix (three.js, Babylon, model-viewer, AR Quick Look, Scene Viewer).canonical_cidDeterministic geometry-identity hash (order/endian-robust SHA-256 prefix) for caching + dedup.
optimizeRun the full pipeline against a preset (web-mobile · web-desktop · quality-max) with every opt-in pass exposed.batch_optimizeWalk files/dirs and optimize each into out_dir with per-asset reports; resumable, continue-on-error.recipe_searchTPE Bayesian search for the winning recipe under a size/quality budget; optional visual-diff gate.dedup_texturesExtract byte-identical embedded images shared across GLBs into a shared sidecar; per-image savings report.lod_bundleBake high/medium/low LOD tiers + a spatialpack.lod.json manifest for screen-height-driven selection.
commerce_readinessOne verdict — ready / warnings / not-ready — composing ACG conformance + AR parity + geometry, with blockers.autocorrectRepair an asset (floater prune + USDZ-safe material bake + optimize), then re-score with resolved/remaining blockers.batch_autocorrectRepair + re-score a whole catalog into out_dir with a roll-up of readiness-status transitions and total savings.safety_gateCohort-aware quality gate over visual-diff metrics; per-asset verdicts + aggregate pass/fail report.
cohort_recipes_buildRun recipe-search per cohort bucket across a corpus subset; emit a cohort-recipes.json the runtime can look up.cohort_recipes_lookupResolve the recipe for given cohort tags from a cohort-recipes.json manifest (with graceful fallbacks).find_similar_assetsTop-K nearest neighbours by cosine similarity against an on-disk embedding index.recipe_search_with_inheritanceRecipe search seeded from the cached winning recipes of the asset’s k nearest neighbours.
usdz_exportConvert GLB → USDZ for AR Quick Look via the local converter, with an optional post-export validation pass.usdz_validatePure-JS USDZ conformance check — size budget, asset-ref resolution, missing textures, file-size cap.usdc_to_usdaRender binary USDC → USDA text (usdcat-equivalent) so an agent can read scene structure as plain text.splat_to_usdzConvert a Gaussian splat (PLY / .splatz) → Apple ParticleField3DGaussianSplat USDZ + optional RealityKit buffers. Structural conformance, NOT RealityKit-verified.model_readySafari 27 <model> / AR Quick Look readiness verdict for a USDZ — ready / warnings / not-ready with blockers. Documented-constraint conformance, NOT a live render.
compare_imagesPixel-precise PNG diff — differing pixels, MAE, ΔE94 mean/max/p95, Sobel-edge delta, SSIM.phash64-bit DCT-based perceptual hash of a PNG (16-char hex).phash_distanceHamming distance between two pHashes (≤5 near-duplicate, >15 clearly different).
bundle_glb_zipPack a GLB + sidecars into a single .glb.zip with a versioned manifest (per-entry DEFLATE/stored).unbundle_glb_zipExtract a .glb.zip — primary GLB + every sidecar — with CRC32 + manifest cross-checks.list_presetsEnumerate preset ids and their key budget knobs so the agent picks intelligently.explain_budgetThe cohort budget + quantization + meshopt-scheduler tables — pure data for agent reasoning.