# Shopify to ChatGPT Shopping Feed (ACP) + Google Merchant (`agentbuilt/shopify-chatgpt-product-feed`) Actor

Turn any Shopify store into an OpenAI Agentic Commerce Protocol (ACP) product feed for ChatGPT Shopping, plus a Google Merchant feed. Validates every offer against the spec. No app install, no login.

- **URL**: https://apify.com/agentbuilt/shopify-chatgpt-product-feed.md
- **Developed by:** [Matthew Edward](https://apify.com/agentbuilt) (community)
- **Categories:** E-commerce, AI, Agents
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.10 / 1,000 offer row generateds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Shopify to ChatGPT Shopping feed (OpenAI ACP) + Google Merchant feed

Make your Shopify store discoverable and buyable inside ChatGPT. This Actor reads your store's public product catalog (no app install, no login, no API keys), maps every variant to an **OpenAI Agentic Commerce Protocol (ACP) product feed** row, validates each offer against the ACP spec, and gives you ready-to-submit files:

- `acp_feed.json` and `acp_feed.csv` — the ChatGPT Shopping / ACP product feed
- `google_merchant_feed.tsv` — the same catalog as a Google Merchant Center feed (Google Shopping, Gemini shopping surfaces)
- `validation_report.json` — every spec violation, counted by type, with fix recommendations

It also emits one dataset row per offer with `valid` / `errors` so you can review the catalog in a table.

### Who this is for

Shopify merchants and agencies preparing for agentic commerce (ChatGPT Instant Checkout, ACP, Google's Universal Commerce Protocol). If you sell on Shopify and want to know "is my catalog ready for AI shopping agents, and what needs fixing?", this answers it in one run.

### How it works

1. Enter your store URL (e.g. `https://www.allbirds.com`).
2. The Actor fetches `/products.json` (Shopify's public catalog endpoint), detects currency and store name from the storefront, and expands every product into variant-level offers.
3. Each offer is validated: required fields, HTTPS links, price format, availability/condition enums, title length, all-caps titles, duplicate IDs, color/size limits.
4. Feeds and the report are written to the run's key-value store; rows go to the dataset.

Schedule it on Apify to regenerate the feed every 15 minutes, which is the freshness ACP recommends.

### Input

| Field | What it does |
|---|---|
| `storeUrl` | Your Shopify store home URL |
| `maxProducts` | Cap on products (variants are expanded automatically) |
| `sellerName` | Merchant name shown to shoppers; auto-detected if empty |
| `currency` | ISO 4217; auto-detected from the storefront |
| `shipping` | Default ACP shipping string `country:region:service:price` (e.g. `US::Standard:5.99 USD`) |
| `condition` | `new` / `refurbished` / `used` (applied to all offers) |
| `onlyAvailable` | Skip out-of-stock variants |
| `sellerPrivacyPolicyUrl`, `sellerTosUrl` | Required by ACP if you enable checkout; default to your Shopify policy pages |

### Output (dataset row example)

```json
{
  "type": "offer",
  "id": "41234567890123",
  "item_group_id": "7123456789012",
  "title": "Wool Runner - Natural Black / 10",
  "description": "Our classic everyday sneaker ...",
  "link": "https://www.allbirds.com/products/mens-wool-runners?variant=41234567890123",
  "image_link": "https://cdn.shopify.com/s/files/.../wool-runner.jpg",
  "price": "110.00 USD",
  "availability": "in_stock",
  "condition": "new",
  "brand": "Allbirds",
  "color": "Natural Black",
  "size": "10",
  "seller_name": "Allbirds",
  "seller_url": "https://www.allbirds.com",
  "valid": true,
  "errors": []
}
```

### Pricing

- **product** — per offer row emitted (one per variant)
- **report** — one per run

A 300-product store with ~4 variants each is ~1,200 product events + 1 report. No platform-usage surcharge.

### Limits and honesty notes

- Works only for Shopify stores that expose `/products.json` (the default; a minority of stores disable it). If yours doesn't, the Actor stops without charging you.
- This produces the feed files; submitting them to OpenAI or Google is done in their merchant consoles. Inventory quantities are not in the public catalog, so availability is in-stock / out-of-stock only.
- Shipping is set from your input; per-region rates are not read from Shopify settings.

### About this Actor

Built and maintained by **agentbuilt** (https://agentbuilt.dev), an AI-operated studio (code, docs, and support handled by an AI agent, with a human owner accountable for the account). Report issues in the **Issues** tab.

# Actor input Schema

## `storeUrl` (type: `string`):

Store home URL, e.g. https://www.allbirds.com. The store must expose the public /products.json endpoint (most do).

## `maxProducts` (type: `integer`):

Cap on products (not variants). Use a large number for the full catalog.

## `sellerName` (type: `string`):

Shown to shoppers in ChatGPT. Defaults to the store's site name.

## `currency` (type: `string`):

Auto-detected from the storefront; set to override, e.g. USD, CAD, EUR.

## `shipping` (type: `string`):

ACP shipping string country:region:service:price, e.g. US::Standard:5.99 USD. Leave empty if you will add shipping later.

## `condition` (type: `string`):

Applied to all offers.

## `onlyAvailable` (type: `boolean`):

Skip variants that are out of stock.

## `sellerPrivacyPolicyUrl` (type: `string`):

Required by ACP if you enable checkout. Defaults to {store}/policies/privacy-policy.

## `sellerTosUrl` (type: `string`):

Required by ACP if you enable checkout. Defaults to {store}/policies/terms-of-service.

## `proxyConfiguration` (type: `object`):

Usually not needed; a few stores block datacenter IPs — use Apify residential proxy then.

## Actor input object example

```json
{
  "storeUrl": "https://www.allbirds.com",
  "maxProducts": 100,
  "condition": "new",
  "onlyAvailable": false,
  "proxyConfiguration": {
    "useApifyProxy": false
  }
}
```

# Actor output Schema

## `results` (type: `string`):

One item per offer/variant in ACP format with validation results, plus one report item.

## `acpFeedJson` (type: `string`):

No description

## `acpFeedCsv` (type: `string`):

No description

## `googleFeedTsv` (type: `string`):

No description

## `report` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "storeUrl": "https://www.allbirds.com"
};

// Run the Actor and wait for it to finish
const run = await client.actor("agentbuilt/shopify-chatgpt-product-feed").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "storeUrl": "https://www.allbirds.com" }

# Run the Actor and wait for it to finish
run = client.actor("agentbuilt/shopify-chatgpt-product-feed").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "storeUrl": "https://www.allbirds.com"
}' |
apify call agentbuilt/shopify-chatgpt-product-feed --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,agentbuilt/shopify-chatgpt-product-feed"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/rA3d35BMEVGJr6Z5g/builds/BFRvovSK52iMw6dZx/openapi.json