`diffbot_extract`

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

Extract the structured content (title, text, author) from — Diffbot analyzes any web page and returns its type, title, cleaned body text, author, publish date, site name, and language. Example: diffbot_extract({ url: “https://example.com/article”, _apiKey: “your-token” })

Parameters

Name	Type	Required	Description
`url`	string	yes	The URL to extract structured content from, e.g. “https://example.com/article”
`_apiKey`	string	yes	Diffbot API token (free 10,000-credit tier, no card, at diffbot.com)

Example call

Arguments

{
  "url": "https://techcrunch.com/2024/01/15/ai-startup-raises-funding/",
  "_apiKey": "your-diffbot-api-key"
}

curl

curl -X POST https://gateway.pipeworx.io/diffbot/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"diffbot_extract","arguments":{"url":"https://techcrunch.com/2024/01/15/ai-startup-raises-funding/","_apiKey":"your-diffbot-api-key"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('diffbot_extract', {
  "url": "https://techcrunch.com/2024/01/15/ai-startup-raises-funding/",
  "_apiKey": "your-diffbot-api-key"
});

Connect

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

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

See Getting Started for client-specific install steps.

diffbot_extract