firecrawlsearchagent_firecrawl_extract_web_data

Extract structured data from web pages using natural language instructions. Specify URLs or domains and define precise extraction criteria to retrieve targeted information for analysis.

Instructions

Extract structured data from one or multiple web pages using natural language instructions using Firecrawl. This tool can process single URLs or entire domains (using wildcards like example.com/*). Use this when you need specific information from websites rather than general search results. You must specify what data to extract from the pages using the 'extraction_prompt' parameter.

Input Schema

Name	Required	Description	Default
`extraction_prompt`	Yes	Natural language description of what data to extract from the pages.
`urls`	Yes	List of URLs to extract data from. Can include wildcards (e.g., 'example.com/*') to crawl entire domains.

Input Schema (JSON Schema)

{
  "properties": {
    "extraction_prompt": {
      "description": "Natural language description of what data to extract from the pages.",
      "type": "string"
    },
    "urls": {
      "description": "List of URLs to extract data from. Can include wildcards (e.g., 'example.com/*') to crawl entire domains.",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "urls",
    "extraction_prompt"
  ],
  "type": "object"
}

Mesh Agent MCP Server