scrollport

Extract named datapoints from a company site by domain

Define the fields you want — name, description, type and an example each — and get them extracted from the company's own website, with…

by Brand.devReady to run$0.0350 per request · $3.50 per 100 requests

Example

You ask your agent

“How does Stripe charge its customers? Check stripe.com.”

You get

Datapoint name
pricing_model
Datapoint value
Integrated per-transaction pricing with no hidden fees
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": "brand-dev.brand-ai-query",
  "input": {
    "domain": "stripe.com",
    "data_to_extract": [
      {
        "datapoint_name": "pricing_model",
        "datapoint_type": "text",
        "datapoint_example": "per-transaction percentage fee",
        "datapoint_description": "How the company charges customers"
      }
    ]
  }
}

Response

{
  "data": {
    "domain": "stripe.com",
    "status": "ok",
    "data_extracted": [
      {
        "datapoint_name": "pricing_model",
        "datapoint_value": "Integrated per-transaction pricing with no hidden fees"
      }
    ]
  }
}

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 Extract named datapoints from a company site by domain (tool ID: brand-dev.brand-ai-query). 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.

Questions

Is Extract named datapoints from a company site by domain (Brand.dev) free?

Scrollport has no free tier: it costs $0.0350 per request ($3.50 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 Brand.dev?

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

Details

About this tool

Define the fields you want — name, description, type and an example each — and get them extracted from the company's own website, with the URLs used Request one bounded result or page using the documented fields. Pagination is explicit: follow-up pages require another run. The catalog price is the maximum per request; the upfront quote reflects the selected limits. Completed requests cost that quote, including valid empty pages and no-match answers. Supplier waivers do not change the customer price. Failed requests are uncharged. Results contain reviewed business data and available pagination. The worked example shows selected fields from a recorded response, with at most the first item of each list.

All inputs and outputs

Input

data_to_extractarray · required

minItems: 1 · maxItems: 10

domainstring · required

bare domain, no scheme

minLength: 1 · maxLength: 253

Output

dataobject

Main result payload.

Errors and limits
  • invalid_input: The lookup fields or limits are invalid.example: {"domain":"stripe.com","data_to_extract":[{"datapoint_name":"pricing_model","datapoint_description":"How the company charges customers","datapoint_example":"per-transaction percentage fee","datapoint_type":"text"}]}
  • upstream_error: The provider could not complete a verified result; the wallet was not charged.Check the documented fields and contact Scrollport support with the run ID if needed.