scrollport

Firecrawl Search

Search public web pages for URLs, titles and snippets.

by FirecrawlReady to run$0.0280 per request · $2.80 per 100 requests

Example

You ask your agent

“Search example.com for “Example Domain” and give me the top results.”

You get

Title
Example Domain
URL
https://example.com/
Description
# Example Domain This domain is for use in documentation examples without needing permission.
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-search",
  "input": {
    "limit": 2,
    "query": "site:example.com Example Domain"
  }
}

Response

{
  "limit": 2,
  "results": [
    {
      "url": "https://example.com/",
      "title": "Example Domain",
      "description": "# Example Domain\nThis domain is for use in documentation examples without needing permission."
    }
  ],
  "returned_results": 1
}

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 Search (tool ID: firecrawl.web-search). 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 6 →

Questions

Is Firecrawl Search free?

Scrollport has no free tier: it costs $0.0280 per request ($2.80 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

Search public web pages for URLs, titles and snippets, with optional country and recent-time filters. Each completed request, including an empty result, is charged by the requested limit in started blocks of ten slots, up to 100. Result pages are not scraped. The worked example shows selected fields and at most one item per list; counts retain their recorded values.

All inputs and outputs

Input

countrystring · optional

Country used to filter or localise the results.

limitinteger · optional

Maximum number of results to return.

minimum: 1 · maximum: 100

querystring · required

Search terms used to find relevant records.

minLength: 1 · maxLength: 500

tbsstring · optional

enum: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y

Output

limitnumber
resultsarray

Result records.

returned_resultsnumber

Number of results returned.

Errors and limits
  • invalid_input: The URL, query or limits are outside this tool's supported inputs.example: {"query":"site:example.com Example Domain","limit":1}
  • 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.