firecrawl▌

Cloud browser automation for pages requiring clicks, forms, login, and pagination. \n \n Supports interactive workflows: click elements, fill forms, navigate multi-step flows, handle pagination and infinite scroll \n Persistent profiles survive session close, enabling login-then-work patterns where authentication state is retained across reconnects \n Core commands include open , snapshot -i (element discovery with @ref IDs), click , fill , type , scrape , scroll , wait , and eval for JavaScript

$21

Enrich research documents by automatically searching and scraping web sources using the FireCrawl API. Extract research topics from markdown files and generate comprehensive research documents with source material.

Scrape individual web pages and convert them to clean, LLM-ready markdown. Handles JavaScript rendering, anti-bot protection, and dynamic content.

Requires firecrawl server in mcp_config.json with FIRECRAWL_API_KEY.

Web scraping, search, and browser automation CLI. Returns clean markdown optimized for LLM context windows.

Web scraping and content extraction via Firecrawl API with format conversion, page interaction, and batch processing. \n \n Five endpoint modes: scrape single pages, crawl entire websites, map URLs, batch-scrape multiple URLs, and check crawl job status \n Supports multiple output formats including markdown, HTML, JSON with schema extraction, screenshots, and PDF parsing \n Browser automation actions (click, scroll, wait, write, JavaScript execution) enable interaction before content extraction

$21

Convert websites into LLM-ready data with JavaScript rendering, anti-bot bypass, and autonomous agents. \n \n Seven core endpoints: scrape single pages, crawl entire sites, discover URLs, search the web, extract structured data, run autonomous agents, and batch process multiple URLs \n Handles JavaScript rendering, CAPTCHA/bot detection bypass, PDF/DOCX parsing, design system extraction, and content change tracking across multiple output formats (markdown, HTML, JSON, screenshots, summaries) \n

Download entire websites as organized local files in multiple formats. \n \n Maps site structure first, then scrapes each discovered page into nested directories under .firecrawl/ , supporting markdown, links, screenshots, and custom format combinations \n Filters pages by path patterns ( --include-paths , --exclude-paths ), search queries, subdomain inclusion, and page limits to control scope \n All standard scrape options work with download: format selection, full-page screenshots, main-conten