Firecrawl: Search

Search the web and scrape the result pages’ content in one call.

Tool ID: firecrawl_search

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'firecrawl_search',
  {
    "query": "software companies hiring engineers"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute firecrawl_search --input '{
  "query": "software companies hiring engineers"
}' --json

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "data": {
    "web": [
      {
        "url": "https://example.com"
      }
    ],
    "images": [
      {}
    ],
    "news": [
      {}
    ]
  }
}

Use deepline describe firecrawl_search --json for the latest machine-readable contract.

Input reference

Search the web and optionally scrape result pages.

Name	Type	Required	Default	Details
`payload.query`	`string`	Yes	—	Search query (max 500 chars)
`payload.limit`	`integer`	No	—	Max results (default 5, max 100)
`payload.country`	`string`	No	—	Country code (e.g. “us”)
`payload.tbs`	`string`	No	—	Time-based search filter (e.g. “qdr:d” for past day)
`payload.location`	`string`	No	—	Geographic location string
`payload.sources`	`array`	No	—	Search source types
`payload.categories`	`array`	No	—	Search category filters
`payload.timeout`	`integer`	No	—	Request timeout in ms (default 60000)
`payload.ignoreInvalidURLs`	`boolean`	No	—	Skip invalid URLs instead of failing (default false)
`payload.scrapeOptions`	`object`	No	—	Options for scraping search results

This input schema is too large for an inline display. Read the complete live contract with deepline describe firecrawl_search --json.

Output reference

Web search results with optional scraped content.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Provider response payload.
`result.data.web`	`array`	No	—	—
`result.data.web[].url`	`string`	Yes	—	—
`result.data.web[].title`	`string`	No	—	—
`result.data.web[].description`	`string`	No	—	—
`result.data.web[].markdown`	`string`	No	—	—
`result.data.images`	`array`	No	—	—
`result.data.news`	`array`	No	—	—
`result.meta`	`record`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: per_result (per result).
Estimated Deepline credits: 0.03 per pricing unit.

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation