firecrawl-mcp-server
Level ARemoteOfficial 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.
Overview
Official Firecrawl MCP server that gives AI clients web context: search the web plus developer, government, and research indexes; scrape any URL into clean Markdown or structured JSON; parse PDFs; crawl or map sites; and interact with pages in a real browser via clicks, typing, and navigation. It also supports Agent jobs for multi-source research, page-change monitoring, credit usage checks, and automatic retries.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"firecrawl-mcp-server": {
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/firecrawl/firecrawl-mcp-server
Known working client config (can write into mcp.json):
{
"mcpServers": {
"firecrawl-mcp-server": {
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
firecrawl-cursor-pluginFirecrawl plugin for Cursor: the context API for AI agents. Hosted MCP server anfireroundWho raised today, in one place. Open-source funding feed built on Firecrawl: verScrapling🕷️ The BEST Web Scraping framework that handles everything from a single requestChrome DevTools MCP谷歌官方:让 AI 操控 Chrome——页面操作、Lighthouse 性能分析、网络监控、控制台日志UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models andPlaywright MCP微软出品的浏览器自动化工具,用结构化快照操控网页:点击、填表、截图、抓取,无需视觉模型