`scrapingbee_ai_extract`

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

Extract structured data from a web page using ScrapingBee’s AI. Pass a natural-language question or field description via ai_query and get back structured JSON. Example: scrapingbee_ai_extract({ url: “https://example.com/product\”, ai_query: “product name and price”, _apiKey: “your-key” })

Parameters

Name	Type	Required	Description
`url`	string	yes	Full target URL including protocol.
`ai_query`	string	yes	Natural-language description of the data to extract, e.g. “the article title, author, and publish date”.
`render_js`	boolean	no	Execute JavaScript via a headless browser before extraction (default true).
`premium_proxy`	boolean	no	Route through residential premium proxies (higher credit cost).
`country_code`	string	no	ISO 3166-1 alpha-2 country code for proxy geolocation, e.g. “us”.
`_apiKey`	string	yes	Your ScrapingBee API key.

Example call

Arguments

{
  "url": "https://example.com/product",
  "ai_query": "product name and price",
  "_apiKey": "your-scrapingbee-api-key"
}

curl

curl -X POST https://gateway.pipeworx.io/scrapingbee/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"scrapingbee_ai_extract","arguments":{"url":"https://example.com/product","ai_query":"product name and price","_apiKey":"your-scrapingbee-api-key"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('scrapingbee_ai_extract', {
  "url": "https://example.com/product",
  "ai_query": "product name and price",
  "_apiKey": "your-scrapingbee-api-key"
});

More examples

{
  "url": "https://news.example.com/article",
  "ai_query": "article title, author name, and publication date",
  "render_js": true,
  "country_code": "gb",
  "_apiKey": "your-scrapingbee-api-key"
}

Connect

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

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

See Getting Started for client-specific install steps.

scrapingbee_ai_extract