`extract`

Pack: tavily · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/extract for the schema, then POST the same URL with its arguments for the data.

Extract clean article text from one or more URLs via Tavily: strips boilerplate/navigation and returns up to 20,000 chars of readable content per page. Accepts a single URL string or an array. Ideal for feeding source pages into an LLM.

Parameters

Name	Type	Required	Description
`urls`	string,array	yes	A single URL string, or an array of URL strings, to extract clean text from.
`items`	string	no
`_apiKey`	string	no	Optional — your own Tavily API key for higher limits; omit to use the shared Pipeworx key.

Example call

Arguments

{
  "urls": "https://www.example.com/article"
}

curl

curl -X POST https://gateway.pipeworx.io/tavily/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"extract","arguments":{"urls":"https://www.example.com/article"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('extract', {
  "urls": "https://www.example.com/article"
});

More examples

{
  "urls": [
    "https://www.example.com/article1",
    "https://www.example.com/article2"
  ]
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

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

Connect to just the tavily pack

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

See Getting Started for client-specific install steps.

extract