ActionFirecrawlUpdated September 2026

How do I run a Firecrawl agent?

Short answer: You can run firecrawl agent in Firecrawl by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Firecrawl Run Firecrawl Agent action to a workflow, map its 4 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Run Firecrawl Agent in Firecrawl — start free All 8 Firecrawl actions

Run Firecrawl Agent in Firecrawl — start free

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Starting URL url	string	Optional	Optional. If blank, the agent runs in discovery mode and decides where to look based on the task + schema. Provide a URL when you want the agent to anchor to a specific page.
Agent Task prompt	string	Required	Natural-language instruction for the agent. Be specific about what to do and what to extract. Examples: "Click the Pricing link and extract every plan name with its monthly price." or "Return the title and points of the top 3 stories from the front page."
Agent Model model	options	Optional	Which Spark model to use. Mini is the Firecrawl API default and works well for most tasks; switch to Pro only if Mini repeatedly fails on a specific page.
Output Schema schema	json_schema	Optional	Define the shape of `data` you want the agent to return. Leave empty to get prose output instead of structured JSON.

Sample request

{
  "url": "e.g. https://news.ycombinator.com",
  "prompt": "e.g. Find the company's contact email on the About or Contact page",
  "model": "{{trigger.model}}",
  "schema": "{{trigger.schema}}"
}

Returns

{
  "data": [
    {
      "title": "I Moved My Digital Stack to Europe",
      "points": 52
    },
    {
      "title": "Deterministic Fully-Static Whole-Binary Translation",
      "points": 218
    },
    {
      "title": "New stainless steel for hydrogen production",
      "points": 97
    }
  ],
  "model": "spark-1-pro",
  "status": "completed",
  "success": true,
  "expiresAt": "2026-05-14T12:58:46.741Z",
  "creditsUsed": 0
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Run Firecrawl Agent.

Any of these apps can fire this action as part of a workflow.

Google Sheets → Firecrawl

2 Google Sheets triggers

HubSpot → Firecrawl

18 HubSpot triggers

FAQ

Questions about Run Firecrawl Agent.

What does the Run Firecrawl Agent action do in Firecrawl?

Runs an agentic browse task — Firecrawl's agent navigates the site and performs the configured extraction goal. For complex scraping that requires sequential page navigation or form interaction.

What inputs does Run Firecrawl Agent require?

Required: Agent Task. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Firecrawl returns an error?

The run history shows the failed step with its input and the error message Firecrawl returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.

Does Run Firecrawl Agent support batch operations?

Run Run Firecrawl Agent inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Firecrawl's rate limits.

More actions