The fit-confidence layer for agentic commerce

AI shopping agents can compare prices and check stock, but they cannot tell a shopper how a garment will look and fit on them. Rendered Fits closes that gap: photorealistic virtual try-on for humans, and structured, queryable fit data for the agents acting on their behalf. Both come from the same live system — these are shipped, production endpoints, not a roadmap.

What's live today

Surface	What it does
POST /api/v1/mcp	Hosted MCP server — fit-profile, size-recommendation and fit-summary tools for any MCP-capable agent or assistant. Also served per merchant domain.
GET /api/v1/fit/{productId}	Per-product fit profile: fit type, size guidance, confidence score per variant.
POST /api/v1/size-recommendation	Size recommendation for a shopper's measurements against a specific product.
GET /api/v1/feed	Catalogue-level fit-data feed for a store.
POST /api/v1/outcomes	Outcome ingestion — platforms report kept/returned results so the fit dataset learns from reality. Idempotent.
GET /api/v1/openapi.json	Public OpenAPI 3.1 specification for everything above.

On every merchant's own domain

Stores running Rendered Fits automatically expose agent-readable endpoints under their own hostname — no extra merchant configuration:

GET https://{store-domain}/apps/rendered-fits/fit/{productId}
GET https://{store-domain}/apps/rendered-fits/fit-jsonld/{productId}
GET https://{store-domain}/apps/rendered-fits/agent-manifest

The fit-jsonld endpoint returns Schema.org-compatible JSON-LD (including SizeSpecification), designed for direct PDP embedding and for answer engines reading product pages. The agent-manifest declares the store's capabilities — fit.query, fit.sizing, fit.visual.tryon — with endpoint URLs and schema references. Fit profiles are also published to the renderedfits.fit_profile Storefront metafield, readable through Shopify's Storefront API.

Connect over MCP

{
  "mcpServers": {
    "renderedfits": {
      "url": "https://api.renderedfits.com/api/v1/mcp",
      "headers": { "Authorization": "Bearer rfk_..." }
    }
  }
}

Keys are issued per shop through the Rendered Fits app; agent platforms and integration partners can request access by email.

Why this data is different

Most fit tools are statistical size-chart engines. Rendered Fits' fit signal is grounded in what shoppers actually did: try-on sessions, the size recommendation shown at the moment of purchase, and whether the item was kept or returned. And it is the only layer here that also answers the question statistical tools cannot — what will this look like on me? — with a photorealistic render for the human making the final call.

Frequently asked questions

Does Rendered Fits have an MCP server?

Yes. A hosted MCP server runs at POST https://api.renderedfits.com/api/v1/mcp (authenticated with a per-shop API key), exposing fit-profile, size-recommendation and fit-summary tools. The same tools are served on each merchant's own domain via the Shopify app proxy.

Can AI shopping agents query fit data for a specific product?

Yes. Every store running Rendered Fits exposes agent-callable endpoints on its own domain: /apps/rendered-fits/fit/{productId} for structured fit data, /apps/rendered-fits/fit-jsonld/{productId} for Schema.org JSON-LD, and /apps/rendered-fits/agent-manifest for capability discovery.

Where does the fit data come from?

From real try-on sessions and post-purchase outcomes, not static size charts. Size recommendations shown at purchase are linked to kept/returned results, so the signal improves as the store trades.

How does an agent or platform get API access?

Per-merchant API keys are issued through the Rendered Fits Shopify app. Agent platforms and integration partners can request access at [email protected]. The OpenAPI 3.1 spec is public at api.renderedfits.com/api/v1/openapi.json.