F

Firecrawl MCP

Advanced web scraping and crawling for AI assistants

Official
Browser Automation
Install Command
npx firecrawl-mcp
Claude Desktop Config
{
  "mcpServers": {
    "firecrawl-mcp": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": { "FIRECRAWL_API_KEY": "<YOUR_API_KEY>" }
    }
  }
}

Firecrawl MCP is an officially maintained MCP server in the Browser Automation category, developed by Mendable / Firecrawl. It runs locally on your machine, keeping your data private and giving you full control over the connection. Adding it to your setup expands what Claude can do without any extra coding.

About Firecrawl MCP

Firecrawl MCP server provides powerful web scraping capabilities, turning any website into clean markdown for AI consumption.

Features

  • Scrape any URL and convert to clean Markdown
  • Crawl entire websites with configurable depth
  • Search the web and scrape results
  • Extract structured data from pages
  • Handle JavaScript-rendered content
  • Bypass common scraping blockers

Who Should Use Firecrawl MCP?

  • 1Control a browser and scrape the web through Claude
  • 2Extend Claude and other AI assistants with new capabilities
  • 3Automate tasks that previously required manual steps
  • 4Connect your existing tools to an AI workflow

How to Install Firecrawl MCP

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

  1. 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
  2. 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
  3. 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.

How Firecrawl MCP Compares

It is an officially maintained server — unlike community alternatives, it is built and supported by the original project team, ensuring compatibility with upstream changes.
It runs entirely on your local machine, so no data leaves your environment — important for teams with privacy or compliance requirements.
It is distributed as an npm package, making version management and updates straightforward with a single `npm update` command.

Tags

scrapingcrawlingwebmarkdownfirecrawl

Reviews