Firecrawl - Web Search and Scraping MCP Server

A Model Context Protocol (MCP) server that provides web search and scraping capabilities.

Features

• Search: Search the web using DuckDuckGo
• Scrape: Extract text content from any URL
• Extract Links: Get all links from a webpage

Installation

pip install firecrawl

Usage

Run the server:

firecrawl

Available Tools

1. search

Search the web and get top results.

Parameters:

• query (string, required): Search query
• max_results (number, optional): Maximum results to return (default: 5)

2. scrape

Extract text content from a URL.

Parameters:

• url (string, required): URL to scrape
• include_links (boolean, optional): Include links found on page (default: false)

3. extract_links

Extract all links from a webpage.

Parameters:

• url (string, required): URL to extract links from

Use with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "firecrawl": {
      "command": "firecrawl"
    }
  }
}

Requirements

• Python 3.10+
• requests
• beautifulsoup4
• urllib3

License

MIT