AI 에이전트를 위한 컨텍스트 API인 Firecrawl을 MCP 호환 클라이언트에 전달하는 모델 컨텍스트 프로토콜(MCP) 서버로, 라이브 웹에서 검색, 스크래핑, 상호작용하여 깨끗한 마크다운 또는 구조화된 데이터를 복구합니다.

@vrknetha @knacklabs 초기 구현에 정말 감사드립니다!

특징

• 웹 검색 (선택적으로 각 결과에 대해 전체 페이지 콘텐츠와 함께)
• 개발자 소스 인덱스(GitHub 이슈, 병합된 풀 요청, README, 문서), 미국 정부 출처, 과학 논문(PubMed, bioRxiv, medRxiv, arXiv) 검색
• 어떤 URL이든 깨끗한 Markdown 또는 구조화된 JSON 스크래핑
• 파서 PDF 및 문서
• 여러 페이지에서 콘텐츠를 크롤링하거나 URL을 찾기 위해 매핑
• 실제 브라우저에서 페이지와 상호작용: 클릭, 타이핑, 양식 작성, 동적 페이지 탐색
• 구조화된 데이터를 반환하는 다중 출처 연구를 위한 에이전트 작업 실행
• 페이지를 모니터링하고 내용이 변경될 때 알림을 받는다
• 현재 및 과거 Firecrawl 크레딧 사용 확인
• 자동 재시도 및 속도 제한
• 클라우드 및 자체 호스팅 지원
• SSE 지원

MCP.so의 놀이터나 Klavis AI에서 MCP 서버를 사용해 플레이해 보세요.

언제 이 서버를 사용해야 하는지

Firecrawl MCP Server

A Model Context Protocol (MCP) server that brings Firecrawl, the context API for AI agents, to MCP-compatible clients: search, scrape, and interact with the live web and get back clean Markdown or structured data.

Big thanks to @vrknetha, @knacklabs for the initial implementation!

Features

• Search the web, optionally with full page content for each result
• Search indexes for developer sources (GitHub issues, merged pull requests, READMEs, and docs), US government sources, and scientific papers (PubMed, bioRxiv, medRxiv, arXiv)
• Scrape any URL into clean Markdown or structured JSON
• Parse PDFs and documents
• Crawl a site for content from many pages, or map it to discover its URLs
• Interact with pages in a real browser: click, type, fill forms, and navigate dynamic pages
• Run Agent jobs for multi-source research that returns structured data
• Monitor pages and get notified when their content changes
• 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_scrape when you have a known URL and want its content as markdown or as JSON matching a schema you supply.
• Use firecrawl_map when you need to discover URLs on a site without fetching their content.
• Use firecrawl_crawl when you need content from many pages under a site; set limit, includePaths/excludePaths, or maxDiscoveryDepth to bound it.
• Use firecrawl_search when you’re starting from a query rather than a URL and want ranked web results. Results carry excerpts; fetch full pages with firecrawl_scrape on the URLs you need. scrapeOptions fetches every result’s page in the same call and bills each as a scrape, so keep it for the full text of a few results (the search-only endpoint never fetches content).
• Use firecrawl_interact when a page needs a click, type, or navigate action before you can read it: pass a url for a fresh page or a scrapeId to 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_usage to check credits left or what credits were spent on, by month or day, optionally broken down by endpoint or API key.