Catalog Normalizer MCP Server

Catalog Attribute Normalizer

Clean, normalized product attributes and taxonomy mappings from messy multi-source catalogs — titles, descriptions, images in; consistent attributes, units, and category mappings out. For merchant-ops teams and feed-tool developers wrangling a Shopify export, a supplier CSV, and a marketplace scrape that each spell "size" or "material" differently.

What it does

• Accepts a batch of raw products (title, description, raw_attributes), returns normalized attributes (canonicalized sizes/colors/units) plus category mappings for whichever taxonomies you request (Google Product Taxonomy, Shopify, Amazon).
• Works as an MCP server (normalize_catalog tool) or a plain HTTPS API.

Example (MCP tool call)

{
  "tool": "normalize_catalog",
  "input": {
    "products": [{ "title": "...", "description": "...", "raw_attributes": { "size": "Lrg", "Color": "Navy Blue" } }],
    "target_taxonomies": ["google", "shopify"]
  }
}

{
  "results": [
    {
      "schema_version": "2.0",
      "source_title": "...",
      "category_paths": {
        "google": { "path": ["Apparel & Accessories", "Clothing", "Shirts & Tops"], "leaf_id": null, "confidence": 0.9 },
        "shopify": { "path": ["Apparel & Accessories", "Clothing", "Tops"], "leaf_id": "aa-3-1", "confidence": 0.85 }
      },
      "attributes": {
        "size": { "value": "L", "provenance": "canonicalized" },
        "color": { "value": "navy", "provenance": "canonicalized" }
      }
    }
  ]
}

attributes is keyed by a controlled vocabulary (size, color, material, gender, sleeve_length — unrecognized keys are dropped, not passed through under a model-chosen name). Each value's provenance is "canonicalized" when it came from your own raw_attributes input for that product (deterministic cleanup only, no recall) or "extracted" when the model inferred it from the title/description and it wasn't in your input — treat "extracted" values as a suggestion, the same way you'd treat a low-confidence category_paths entry.

Attributes are reliable by construction — canonicalizing values already in your input, not recall. Category classification is retrieval-grounded, not recalled from memory: candidates are retrieved from the real, current Google and Shopify taxonomy files and offered to the model as suggestions, so a leaf_id almost always names a node that actually exists — measured against a 12-product evaluation set, 22/24 (91.7%) exact path + leaf-ID matches. Still treat confidence and a null leaf_id as "worth a quick check," not a guarantee — a leaf_id is only ever returned when the path independently verifies against the real taxonomy file, so a null there is an honest "check this" signal, never a fabricated ID. Amazon has no comprehensive public taxonomy reference file to retrieve candidates from, so it stays best-effort (recall from memory) rather than retrieval-grounded.

Pricing

• Free — 500 products/month, no card required.
• Pay-as-you-go — $0.01/product, no minimum.
• Pro — $29/month for 5,000 products (~$0.0058/product effective).

Getting a key

The MCP server is live at https://acjlabs-catalog-normalizer.acjlabs.workers.dev/mcp. Free-tier keys self-serve — POST /v1/signup with { "email": "you@example.com" } returns your key directly in the response, good for 500 products/month, no card required. Store it immediately — it is shown once and cannot be recovered if lost (re-signup for a new one). Paid keys provision the same way via a one-time claim link once Pro/pay-as-you-go billing is live.

npm client

Prefer a typed function over hand-rolling MCP JSON-RPC calls? @acjlabs/catalog-attribute-normalizer-client (client/, not published yet — npm publish is a gated founder action) wraps the normalize_catalog tool call:

import { createCatalogNormalizerClient } from "@acjlabs/catalog-attribute-normalizer-client";

const client = createCatalogNormalizerClient({
  baseUrl: "https://acjlabs-catalog-normalizer.acjlabs.workers.dev",
  apiKey: "...",
});
const results = await client.normalizeCatalog(products, ["google", "shopify"]);

Why not just use a category classifier?

Category classifiers (ProductCategorization.com, ProductClassifier.com) tell you what a product is. They don't touch the messier problem: standardizing attributes across sources that each spell them differently. The one vendor doing the broader job, DataWeave, is enterprise sales-led — no self-serve, no public price. See the full comparison, or read why "clean product data" is actually two different problems (canonicalization vs. classification, and why they fail differently).

Source availability & support

This repository hosts the documentation for the hosted service. The service implementation is not open source. Bug reports and feature requests are welcome in this repo's Issues; you can also reach us at contact@acjlabs.com.