ActionFirecrawlUpdated June 2026

How do I search the web with Firecrawl?

Short answer: Drop the "FirecrawlFirecrawl Web Search" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Inputs

The fields this action accepts.

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

FieldTypeRequiredDescription
Query
query
stringRequiredSearch query.
Limit
limit
numberOptionalHow many results to return per source (1–100).
Sources
sources
arrayOptionalWhich result types to fetch. Any combination of: web, images, news. The response splits into data.web / data.images / data.news accordingly.
Scrape Formats
scrape_options_formats
arrayOptionalOptional. Set to e.g. ["markdown"] to scrape each result page inline. Costs more credits but saves a separate scrape pass.
Sample request
{
"query": "{{trigger.query}}",
"limit": "{{trigger.limit}}",
"sources": "{{trigger.sources}}",
"scrape_options_formats": "{{trigger.scrape_options_formats}}"
}
Returns
{
"data": {
"web": [
{
"url": "https://example.com",
"title": "Example page",
"markdown": "# Example\n\nFull content when scrape was requested.",
"description": "A short snippet from the page."
}
],
"news": [],
"images": []
},
"success": true
}

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

Triggered by

Apps that pair well as the trigger for Firecrawl Web Search.

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

FAQ

Questions about Firecrawl Web Search.

What does the Firecrawl Web Search action do in Firecrawl?
Web search bundled with scraping — Firecrawl runs the search and fetches the content of top results in one call. Saves the "search then scrape each result" two-step for grounded-answer workflows.
What inputs does Firecrawl Web Search require?
Required: Query. 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 workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.
Does Firecrawl Web Search support batch operations?
Yes. Run Firecrawl Web Search inside a Loop node to process arrays. Tiny Command handles Firecrawl's rate limits automatically so you don't have to throttle manually.
More actions

Other Firecrawl actions.

Action
Crawl Site
Starting from a URL, Firecrawl follows links and fetches every page within scope. Returns markdown-formatted content of each. For "ingest a docs site into a RAG index" or "build a knowledge base from a brand's blog" workflows.
Action
Extract Structured Data
Pass a URL and a schema; Firecrawl extracts matching fields. For "scrape product details from this page into our DB" workflows where you want typed JSON rather than raw HTML.
Action
Get Firecrawl Agent Result
Polls an agent task for completion and returns the result. For Firecrawl's agentic-scraping workflows that perform multi-step browse tasks.
Action
Get Crawl Status
Returns the current status of a running crawl — pages crawled, pages discovered, completion percentage. Poll until status=completed before consuming results.
Action
Map Site URLs
Returns the URL list of a site without fetching content — the fast preflight before deciding what to crawl. Useful for "find all pages under /blog" or "count pages on this competitor's site" inventory workflows.
Action
Run Firecrawl Agent
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.

Send firecrawl web search from your workflows.

Triggered by anything in the catalog. Free tier available. No credit card.