extract_data
Start a Firecrawl v2 extraction job that uses AI to transform one or more web pages into structured data. Supports wildcard URLs, natural-language prompts, JSON Schema output, optional web search, and scrape options for source pages.
map_website
Map a website with Firecrawl v2 and retrieve discovered URLs quickly. Use this before scraping or crawling when you need a site inventory or relevant URLs from a domain.
crawl_website
Start a Firecrawl v2 crawl job to recursively discover and scrape pages from a website. The crawl runs asynchronously and returns a crawl ID for polling, cancellation, error retrieval, and webhook events.
get_agent_status
Check a Firecrawl agent job and retrieve gathered data when complete.
run_agent
Start a Firecrawl v2 agent job for autonomous web data gathering. Use this for open-ended research or extraction tasks where Firecrawl should search, navigate, and gather data from one or more sites.
get_extract_status
Check a Firecrawl extract job and retrieve structured data when complete.
get_batch_scrape_status
Check a Firecrawl batch scrape job and retrieve available page data. Use this with the batchId returned by Batch Scrape. Use Get Batch Scrape Errors for failed URLs and Cancel Batch Scrape to stop a running job.
scrape_page
Scrape a single URL with Firecrawl v2 and extract markdown, HTML, raw HTML, links, screenshots, images, audio/video URLs, structured JSON, summaries, brand data, answers, highlights, or change tracking data. Use this when you have a known URL and need clean page content or a single-page extraction.
get_crawl_status
Check a Firecrawl crawl job and retrieve available page data. Use this with the crawlId returned by Crawl Website. Use Get Crawl Errors for failed pages and Cancel Crawl to stop a running job.
batch_scrape
Start a Firecrawl v2 batch scrape job for a known list of URLs. Batch scrape supports the same extraction options as single-page scraping and returns an asynchronous job ID for polling, cancellation, and error retrieval.
search_web
Search the web with Firecrawl v2 and optionally scrape search results. Supports web, image, and news sources; domain filters; time/location filters; categories; and scrape options for full result content.
get_crawl_errors
Retrieve failed URLs and robots.txt blocked URLs for a Firecrawl crawl job.
parse_file
Upload a file to Firecrawl v2 Parse and convert it into markdown or other extraction formats. Use this for local or non-public documents such as HTML, PDF, DOCX, DOC, ODT, RTF, XLSX, and XLS files.
cancel_crawl
Cancel a running Firecrawl crawl job.
interact_with_page
Continue interacting with the browser state from a prior Firecrawl scrape. Execute Node, Python, or bash code, or provide a natural-language prompt for Firecrawl's page interaction agent.
stop_page_interaction
Stop the interactive browser session associated with a Firecrawl scrape job.
get_scrape_status
Retrieve the status and result data for a Firecrawl scrape job by scrape ID. Use the scrapeId from Scrape Page metadata.
get_queue_status
Get Firecrawl scrape queue metrics for the authenticated team.
list_browser_sessions
List Firecrawl browser sandbox sessions for the authenticated team.
cancel_agent
Cancel a running Firecrawl agent job.
get_credit_usage
Get remaining Firecrawl credits for the authenticated team.
create_browser_session
Create a Firecrawl browser sandbox session for interactive web automation. Returns CDP and live view URLs for connecting to or observing the session.
get_monitor_check
Get a Firecrawl monitor check and page results.
list_activity
List recent Firecrawl API activity for the authenticated team.
run_monitor
Queue a manual Firecrawl monitor check.
list_monitor_checks
List checks for a Firecrawl monitor.
get_batch_scrape_errors
Retrieve failed URLs for a Firecrawl batch scrape job.
get_token_usage
Get remaining Firecrawl extract tokens for the authenticated team.
create_monitor
Create a Firecrawl monitor for scheduled scrape or crawl checks with webhook or email notifications.
preview_crawl_params
Preview Firecrawl crawl parameters generated from a prompt and explicit crawl options without starting a crawl job.
get_active_crawls
List active Firecrawl crawl jobs for the authenticated team.
get_monitor
Get a Firecrawl monitor by ID.
cancel_batch_scrape
Cancel a running Firecrawl batch scrape job.
delete_browser_session
Delete a Firecrawl browser sandbox session and release its resources.
execute_browser_code
Execute Node, Python, or bash code in an active Firecrawl browser sandbox session.
delete_monitor
Delete a Firecrawl monitor.
list_monitors
List Firecrawl monitors for the authenticated team.
update_monitor
Update a Firecrawl monitor's schedule, targets, notifications, goal, retention, or status.
get_historical_token_usage
Get historical Firecrawl extract token usage for the authenticated team.
get_historical_credit_usage
Get historical Firecrawl credit usage for the authenticated team.