MCP server

Firecrawl MCP

Turns web pages and whole sites into markdown an agent can read.

Save Visit website ↗

Add it to your client

Official

Install

npx -y firecrawl-mcp

mcpServers

{
  "mcpServers": {
    "firecrawl-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ]
    }
  }
}

Transport: both
Runtime: Node
Auth: Required
License: MIT

Tools

firecrawl_scrapefirecrawl_searchfirecrawl_mapfirecrawl_crawlfirecrawl_parsefirecrawl_agentfirecrawl_interact

Repositoryhttps://github.com/firecrawl/firecrawl-mcp-server

Firecrawl handles the parts of scraping that break a plain HTTP fetch: JavaScript-rendered pages, pagination and site-wide crawls. Through MCP it offers single-page scraping, sitemap mapping, long-running crawl jobs you start and then poll, and a search tool that returns page content instead of a bare link list. It runs against Firecrawl's API with a key, or against a self-hosted install.

Comments(0)

No comments yet — be the first.

Similar MCP servers

GitHub MCP Server

MCP server

GitHub's own server for repos, issues, pull requests and workflow runs

Developer ToolsVersion Control & Repos

Playwright MCP

MCP server

Gives an assistant a real browser to click, type and read pages with

Browsers & AutomationDeveloper Tools

Fetch (MCP Reference Server)

MCP server

Reference server that retrieves a URL and hands back markdown.

Developer ToolsSearch Engines & Web