Firecrawl

Scrape, search, map and crawl websites into clean markdown for AI.

5 actions API key 4 read1 write Calls api.firecrawl.dev

Connect

TypeScript

const conn = await setu.connections.initiate({ userId: "user_1", toolkit: "firecrawl" });
console.log(conn.connectUrl); // show this to your user
await conn.waitUntilActive();

Permissions requested

This toolkit uses a single credential and requests no scopes.

Actions

Get crawl statusreadfirecrawl.get_crawl_statusCheck a crawl job by id and get its status, progress counts and the pages scraped so far.

Input	Type		Description
`id`	string	Required	Crawl job id returned by start_crawl

TypeScript

await setu.execute({
  userId: "user_1",
  action: "firecrawl.get_crawl_status",
  input: {
    "id": "<id>"
  },
});

Map a websitereadfirecrawl.mapList the URLs of a website quickly, optionally ordered by relevance to a search term.

Input	Type		Description
`url`	string	Required	Base URL to map
`search`	string	Optional	Order results by relevance to this query
`sitemap`	string	Optional	How to use the sitemap
`includeSubdomains`	boolean	Optional	Include subdomains (default true)
`limit`	integer	Optional	Maximum links, up to 100000 (default 5000)

TypeScript

await setu.execute({
  userId: "user_1",
  action: "firecrawl.map",
  input: {
    "url": "<url>"
  },
});

Scrape a pagereadfirecrawl.scrapeScrape one URL and return its content as markdown (or other formats) plus metadata.

Input	Type		Description
`url`	string	Required	URL to scrape
`formats`	array of string	Optional	Output formats, e.g. markdown, html, links, summary (default markdown)
`onlyMainContent`	boolean	Optional	Return only the main content (default true)
`waitFor`	integer	Optional	Milliseconds to wait before scraping
`timeout`	integer	Optional	Timeout in milliseconds

TypeScript

await setu.execute({
  userId: "user_1",
  action: "firecrawl.scrape",
  input: {
    "url": "<url>"
  },
});

Search the webreadfirecrawl.searchSearch the web and optionally scrape each result into markdown. Returns web results with titles, URLs and descriptions.

Input	Type		Description
`query`	string	Required	Search query (max 500 characters)
`limit`	integer	Optional	Number of results, 1 to 100 (default 10)
`includeDomains`	array of string	Optional	Only these hostnames (not with excludeDomains)
`excludeDomains`	array of string	Optional	Never these hostnames
`tbs`	string	Optional	Time filter, e.g. qdr:w for the past week
`country`	string	Optional	ISO country code (default US)
`scrapeOptions`	object	Optional	Scrape settings for each result, e.g. {"formats": ["markdown"]}

TypeScript

await setu.execute({
  userId: "user_1",
  action: "firecrawl.search",
  input: {
    "query": "<query>"
  },
});

Start a crawlwritefirecrawl.start_crawlStart an asynchronous crawl of a website from a base URL. Returns a job id to poll with get_crawl_status.

Input	Type		Description
`url`	string	Required	Base URL to start crawling from
`limit`	integer	Optional	Maximum pages to crawl
`maxDiscoveryDepth`	integer	Optional	Maximum link depth from the start page
`includePaths`	array of string	Optional	Regex patterns of paths to include
`excludePaths`	array of string	Optional	Regex patterns of paths to exclude
`allowExternalLinks`	boolean	Optional	Follow external links one hop
`allowSubdomains`	boolean	Optional	Follow subdomains
`scrapeOptions`	object	Optional	Per-page scrape settings, e.g. {"formats": ["markdown"]}

TypeScript

await setu.execute({
  userId: "user_1",
  action: "firecrawl.start_crawl",
  input: {
    "url": "<url>"
  },
});