Firecrawl MCP Server
A Model Context Protocol (MCP) server that brings Firecrawl to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context.
Big thanks to @vrknetha, @knacklabs for the initial implementation!
Features
- Search the web and get full page content
- Search an index built for coding agents: GitHub issues, merged pull requests, READMEs, and docs
- Scrape any URL into clean, structured data
- Interact with pages — click, navigate, and operate
- Deep research with autonomous agent
- Check current and historical Firecrawl credit usage
- Automatic retries and rate limiting
- Cloud and self-hosted support
- SSE support
Play around with our MCP Server on MCP.so's playground or on Klavis AI.
When to Use This Server
- Use
firecrawl_scrapewhen you have a known URL and want its content as markdown or as JSON matching a schema you supply. - Use
firecrawl_mapwhen you need to discover URLs on a site without fetching their content. - Use
firecrawl_crawlwhen you need content from many pages under a site; setlimit,includePaths/excludePaths, ormaxDiscoveryDepthto bound it. - Use
firecrawl_searchwhen you're starting from a query rather than a URL and want ranked web results; addscrapeOptionsif you also want page content fetched in the same call (the search-only endpoint never fetches content). - Use
firecrawl_interactwhen a page needs a click, type, or navigate action before you can read it — pass aurlfor a fresh page or ascrapeIdto continue on one you already scraped. - Use the
firecrawl_monitor_*tools when the same page needs to be checked on a recurring schedule with diffs and change alerts, rather than fetched once. - Use
firecrawl_credit_usageto check credits left or monthly consumption, optionally broken down by API key. - Consider something else when you need to hold a browser session open across many of your own steps with your own retry and termination logic: each
firecrawl_interactcall runs onepromptorcodeturn to completion and returns control — the session can persist across calls viascrapeIdand ends withfirecrawl_interact_stop, but you cannot drive it interactively step-by-step from the client side within a single call.






