`zyte_extract`

Pack: zyte · Endpoint: https://gateway.pipeworx.io/zyte/mcp

AI-powered automatic extraction of structured data from a web page. Set type to ‘product’ for e-commerce product pages (name, price, currency, images, SKU, availability…) or ‘article’ for news/blog pages (headline, author, date, body text…). Example: zyte_extract({ url: “https://shop.example.com/item/123\”, type: “product”, _apiKey: “your-key” })

Parameters

Name	Type	Required	Description
`url`	string	yes	The URL of the product or article page to extract
`type`	string	no	What to extract: ‘product’ (e-commerce) or ‘article’ (news/blog). Default ‘product’.
`_apiKey`	string	yes	Zyte API key

Example call

Arguments

{
  "url": "https://shop.example.com/product/laptop-123",
  "type": "product",
  "_apiKey": "your-zyte-api-key"
}

curl

curl -X POST https://gateway.pipeworx.io/zyte/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"zyte_extract","arguments":{"url":"https://shop.example.com/product/laptop-123","type":"product","_apiKey":"your-zyte-api-key"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('zyte_extract', {
  "url": "https://shop.example.com/product/laptop-123",
  "type": "product",
  "_apiKey": "your-zyte-api-key"
});

More examples

{
  "url": "https://news.example.com/article/breaking-news",
  "type": "article",
  "_apiKey": "your-zyte-api-key"
}

Connect

Add this to your MCP client config, or use one-click install buttons:

{
  "mcpServers": {
    "zyte": {
      "url": "https://gateway.pipeworx.io/zyte/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

zyte_extract