Firecrawl Scrape

Scrape a URL with Firecrawl (renders JS, handles anti-bot).

What it does

A managed scrape for pages the simple one cannot read: JavaScript-rendered, behind anti-bot protection, or otherwise hostile. Costs money per page, so use it when Scrape Website has already failed.

What you need

API key from Firecrawl. firecrawl.dev → Dashboard → API Keys.

Connecting it

Credentials belong to one project, not to your workspace and not to you. A system built for one client never runs on another client's account, and a package handed to a business runs on theirs.

Open the project and stay on the Visual Editor tab.
Open the Tools & Integrations rail on the right.
Find this tool, open it, and paste the credential.

To change it later, open the same panel — you can leave the key blank to keep the stored one and change only the other field.

Using it in a step

An Action step runs one tool with the arguments you type, exactly as written, with no model involved — so it costs nothing per run and behaves the same every time. Add one from the canvas toolbar, choose Firecrawl Scrape, and fill in:

Field	Required	What goes in it
`url`	yes	A public page, including ones that need JavaScript to render.

Values can carry results forward: {{previous}} is the step before, and {{row:column}} is a column from the row this run is about when the trigger fans out.

Press Try it to run the step on its own before committing to a whole sequence.

Using it with an agent

Tick Firecrawl Scrape on any agent that should be able to call it, and the agent decides when to. Use an agent when the judgement matters and an Action step when the certainty does.

A worked example

A retailer tracks three competitor prices. Two work with the free scraper; the third is a React storefront that returns an empty shell, and this reads it properly.

When it goes wrong

A bad key returns an error string rather than crashing the run. The step will say so in the trace, and the rest of the sequence carries on.