extract

Active

declared in 0.1.0

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 schema

{
  "type": "object",
  "required": [
    "urls"
  ],
  "properties": {
    "urls": {
      "type": [
        "string",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "A single URL string, or an array of URL strings, to extract clean text from."
    },
    "_apiKey": {
      "type": "string",
      "description": "Optional — your own Tavily API key for higher limits; omit to use the shared Pipeworx key."
    }
  }
}

What this tool wraps· 1 endpoint

min confidence0.70 0.50

Data resourceTavily Search API
Tavily · search
name mention0.85

Parent server

Tavily

https://github.com/pipeworx-io/mcp-tavily

1/7 registries

View full server →