Firecrawl Scrape

Read one public web page as Markdown, HTML or links.

by FirecrawlReady to run$0.0025 per request · $0.25 per 100 requests

Example

You ask your agent

“Read this page and give me its main content as clean text: scrollport.com/examples/recruitment-shortlist.html”

You get

Title: Recruitment shortlist — Scrollport sample
URL: https://scrollport.com/examples/recruitment-shortlist.html
Markdown: # Recruitment shortlist

What your agent sends and gets back (JSON)

Your agent works out the exact inputs, such as IDs, dates and settings, from what you ask.

Request

{
  "tool_id": "firecrawl.web-scrape",
  "input": {
    "url": "https://scrollport.com/examples/recruitment-shortlist.html",
    "formats": [
      "markdown"
    ],
    "onlyMainContent": true
  }
}

Response

{
  "url": "https://scrollport.com/examples/recruitment-shortlist.html",
  "title": "Recruitment shortlist — Scrollport sample",
  "status": 200,
  "markdown": "# Recruitment shortlist",
  "truncated": false
}

Use it with your agent

Copy the prompt and paste it into your agent, then tell it what you need.

Read https://scrollport.com/start. Use my existing Scrollport connection, or help me connect if needed. Help me use Firecrawl Scrape (tool ID: firecrawl.web-scrape). Ask me for the details you need, then show me the result.

Provider access is included. If your agent isn't connected to Scrollport yet, it will help you set that up.

Other tools for this job

Compare all 2 →

Web ScrapeBright Data$0.0033 per request$0.0033 per request

Questions

Is Firecrawl Scrape free?

Scrollport has no free tier: it costs $0.0025 per request ($0.25 per 100 requests), paid per use from a prepaid wallet with no subscription. Connecting your first agent adds $1 of trial credit, so you can try it before adding funds.

Do I need an API key from Firecrawl?

No. Your agent runs it through your Scrollport connection (MCP, the Scrollport CLI or the HTTP API), and Scrollport handles access to Firecrawl, so you don't sign up with Firecrawl or manage an API key.

Details

About this tool

Read one public HTTPS web page as Markdown, HTML, raw HTML or links. Each text format is capped at 100,000 characters and links at 1,000, with truncation reported. PDF documents, X/Twitter, screenshots, JSON extraction, custom headers and browser actions are excluded. Failed or empty page extraction is not charged. The worked example shows selected fields and at most one item per list; counts retain their recorded values.

All inputs and outputs

Input

formatsarray · optional

Output formats to return.

minItems: 1 · maxItems: 4

onlyMainContentboolean · optional

Whether to return only the page's main content.

urlstring · required

Public HTTPS web page. PDF files and X/Twitter URLs are excluded.

format: uri · maxLength: 2048

Output

markdownstring

Page content as Markdown.

statusnumber

Status of the record or request.

titlestring

Title of the record.

truncatedboolean

Whether the result was shortened to fit the response limit.

urlstring

URL of the record.

Errors and limits

invalid_input: The URL, query or limits are outside this tool's supported inputs.example: {"url":"https://example.com/","formats":["markdown"]}
upstream_error: The provider could not return usable results; the wallet was not charged.Check the target page and retry with a smaller limit if necessary.