Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
firecrawl/firecrawl-mcp-server
Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.
- Stars
- 7,877
- +7 days
- —
- Forks
- 943
- Language
- JavaScript
- License
- MIT
- Last push
- 21 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This Model Context Protocol server connects AI agents and MCP clients to Firecrawl web data services. It enables tools to search the web, scrape URLs into clean Markdown, crawl entire websites, and map sitemaps. Developers can also interact with dynamic web pages using browser actions, parse documents, and run structured research agents.
Use it when
- When searching the web or scraping specific URLs into clean Markdown for AI context
- When discovering site structure with mapping or crawling multiple pages under a domain
- When automating browser interactions like clicking and filling forms before reading dynamic pages
Install
npm install -g firecrawl-mcpCommands quoted from the repo's README. Read the README before running them.
Needs a token or API key.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.