Shopify MCP Server: Products & Prices for AI Agents

Give Claude, ChatGPT, Cursor or your own agent live public Shopify data through MCP: product search, product details, collections, store tech stack, Shopify App Store app info and any product page. $0.005 per tool call.

Quick start

1. Press Start. The form is already filled with this example input, so the first run returns real rows in under a minute:

{
  "tool": "shopify_search_products",
  "arguments": {
    "store": "allbirds.com",
    "query": "runner",
    "limit": 5
  }
}

2. Swap in your own values, or call the Actor through the Apify API, Make, Zapier, n8n or the Python/JS clients with the same JSON.
3. Download the results as JSON, CSV or Excel from the Output tab, or schedule the run to repeat.

Tools

Tool	What it returns
shopify_search_products	Products of any Shopify store, with optional text filter, collection and on-sale filter: title, vendor, type, price range, sale and stock flags
shopify_get_product	One product with every variant (SKU, price, compare-at price, availability)
shopify_list_collections	A store's collections with product counts
shopify_detect_store	Is it Shopify? Theme, currency, country, detected apps and tools
shopify_app_info	Shopify App Store listing: developer, rating, review count, pricing plans, categories, languages, integrations (no individual reviews or reviewer names)
product_page_extract	Name, brand, SKU/GTIN, price, stock and rating from any product page on any platform

Sample tool result (real run, trimmed)

{
  "handle": "judgeme",
  "name": "Judge.me Product Reviews App",
  "developer": "Judge.me",
  "rating": 5,
  "reviewCount": 49107,
  "categories": ["Product reviews", "SEO"],
  "hasFreePlan": true,
  "pricingPlans": [{"name": "Forever Free", "price": "Free"}, {"name": "Awesome", "price": "$15 / month"}],
  "launched": "June 25, 2015"
}

Connect your agent

The server runs in Apify Standby mode. Add it to any MCP client that supports Streamable HTTP:

{
  "mcpServers": {
    "shopify-data": {
      "url": "https://mrslm-data--shopify-data-mcp-server.apify.actor/mcp",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Put your own Apify API token (Console > Settings > API & Integrations) in place of <YOUR_APIFY_TOKEN>. The same URL is shown on the Actor's Standby tab.

Run tools without an agent

Start a normal run, pick a Tool and its Tool arguments (or list several in Several tool calls). Each call becomes one dataset row with its result.

Who uses this

• AI shopping and research agents: answer "what does this store sell and for how much?" with live data.
• E-commerce analysts: ask an assistant to compare competitors' catalogs, prices and tech stacks.
• Shopify app makers: let an agent look up rival apps' ratings and pricing plans.

Pricing

$0.005 per successful tool call (Silver $0.0045, Gold $0.004) + $0.00005 per run. Failed calls (store not found, not Shopify, blocked by robots.txt) are free. Each call makes a few polite requests to public pages only.

FAQ

Do I need a Shopify API key or store access? No. The tools read only what every Shopify store publishes to visitors (public catalog JSON and pages). You only need your Apify token.

Which MCP clients work? Any client that supports remote MCP over Streamable HTTP, such as Claude Desktop (via a remote connector), Cursor, VS Code and agent frameworks with MCP support.

What does a typical agent session cost? About $0.005 per successful tool call, so 200 calls cost about $1. Failed calls are free.

Can I use it without an AI agent? Yes. Start a normal run with a tool and its arguments (see the Quick start), and each call becomes a dataset row.

Does it work on non-Shopify stores? product_page_extract works on most product pages on any platform. shopify_app_info reads the Shopify App Store. The store tools need a Shopify store; on other sites the call fails and is not charged.

Is it legal?

This Actor only reads pages and feeds that the website itself publishes to every visitor without a login. It obeys each site's robots.txt, keeps a polite request rate, and never tries to get past logins, paywalls, captchas or bot checks. It does not collect personal data such as emails, phone numbers or names of private individuals. You are responsible for how you use the data: follow the source site's terms, copyright and the privacy laws that apply to you (GDPR, CCPA, etc.). This tool is independent and not affiliated with or endorsed by the platforms it reads.