Firecrawl

Browse the web and get markdown outputs.

Authentication

This connector uses Token-based authentication.

info

Set up your connection in the Abstra Console before using it in your workflows.

How to use

Using the Smart Chat

Execute the action "CHOOSE_ONE_ACTION_BELOW" from my connector "YOUR_CONNECTOR_NAME" using the params "PARAMS_HERE".

Using the Web Editor

from abstra.connectors import run_connection_action

result = run_connection_action(
  connection_name="your_connection_name",
  action_name="your_action_name",
  params={
    "param1": "value1",
    "param2": "value2"
  })

Available Actions

This connector provides 20 actions:

Action	Purpose	Parameters
post_scrape	Scrape a single URL and optionally extract information using an LLM	data (undefined) required
post_batch_scrape	Scrape multiple URLs and optionally extract information using an LLM	data (undefined) required
get_batch_scrape_by_id	Get the status of a batch scrape job	id (string)
delete_batch_scrape_by_id	Cancel a batch scrape job	id (string)
get_batch_scrape_by_id_errors	Get the errors of a batch scrape job	id (string)
get_crawl_by_id	Get the status of a crawl job	id (string)
delete_crawl_by_id	Cancel a crawl job	id (string)
get_crawl_by_id_errors	Get the errors of a crawl job	id (string)
post_crawl	Crawl multiple URLs based on options	data: { . url (string) . excludePaths (array) . includePaths (array) . maxDepth (integer) . maxDiscoveryDepth (integer) . ignoreSitemap (boolean) . ignoreQueryParameters (boolean) . limit (integer) . allowBackwardLinks (boolean) . allowExternalLinks (boolean) . delay (number) . webhook (object) . scrapeOptions (object) } (object) required
post_map	Map multiple URLs based on options	data: { . url (string) . search (string) . ignoreSitemap (boolean) . sitemapOnly (boolean) . includeSubdomains (boolean) . limit (integer) . timeout (integer) } (object) required
post_extract	Extract structured data from pages using LLMs	data: { . urls (array) . prompt (string) . schema (object) . enableWebSearch (boolean) . ignoreSitemap (boolean) . includeSubdomains (boolean) . showSources (boolean) . scrapeOptions (object) . ignoreInvalidURLs (boolean) } (object) required
get_extract_by_id	Get the status of an extract job	id (string)
get_crawl_active	Get all active crawls for the authenticated team	No parameters
post_deep_research	Start a deep research operation on a query	data: { . query (string) . maxDepth (integer) . timeLimit (integer) . maxUrls (integer) . analysisPrompt (string) . systemPrompt (string) . formats (array) . jsonOptions (object) } (object) required
get_deep_research_by_id	Get the status and results of a deep research operation	id (string)
get_team_credit_usage	Get remaining credits for the authenticated team	No parameters
get_team_token_usage	Get remaining tokens for the authenticated team Extract only	No parameters
post_search	Search and optionally scrape search results	data: { . query (string) . limit (integer) . tbs (string) . location (string) . timeout (integer) . ignoreInvalidURLs (boolean) . scrapeOptions (object) } (object) required
post_llmstxt	Generate LLMs.txt for a website	data: { . url (string) . maxUrls (integer) . showFullText (boolean) } (object) required
get_llmstxt_by_id	Get the status and results of an LLMs.txt generation job	id (string)