scrape

Active

declared in 0.1.0

Scrape a single URL using Firecrawl's JS-rendering engine and return clean markdown (up to 100,000 chars), page title, and description. Strips navigation/boilerplate by default (only_main_content=true). Supports output formats: markdown, html, rawHtml, links.

Parameters schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL to scrape, e.g. \"https://example.com/article\""
    },
    "_apiKey": {
      "type": "string",
      "description": "Optional — your own Firecrawl API key for higher limits; omit to use the shared Pipeworx key."
    },
    "formats": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Output formats to return (default [\"markdown\"]). Options include \"markdown\", \"html\", \"rawHtml\", \"links\"."
    },
    "only_main_content": {
      "type": "boolean",
      "description": "Strip navigation, footers, and boilerplate, returning just the main content (default true)."
    }
  }
}

What this tool wraps· 1 endpoint

min confidence0.70 0.50

Data resourceFirecrawl API
Firecrawl · search
name mention0.85

Parent server

mcp-firecrawl

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

2/7 registries

View full server →