Firecrawl MCP

Official Firecrawl MCP server for powerful web scraping, crawling, search, and structured data extraction.

автор: Firecrawl

The Firecrawl MCP Server provides powerful web scraping capabilities for AI assistants, including single page scraping, batch operations, site crawling, and structured data extraction.

Installation

NPX

env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp

Global Installation

npm install -g firecrawl-mcp

Configuration

Claude Desktop

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

Cursor

Open Cursor Settings
Go to Features > MCP Servers
Add the configuration above

Available Tools

Tool	Best For	Returns
`firecrawl_scrape`	Single page content	markdown/html
`firecrawl_batch_scrape`	Multiple known URLs	markdown/html[]
`firecrawl_map`	Discovering URLs on a site	URL[]
`firecrawl_crawl`	Multi-page extraction	markdown/html[]
`firecrawl_search`	Web search for info	results[]
`firecrawl_extract`	Structured data from pages	JSON

Features

Web Scraping - Extract content from any webpage
Batch Processing - Scrape multiple URLs efficiently
Site Crawling - Discover and crawl entire websites
Search - Search the web and extract content
Structured Extraction - Extract data using schemas
Automatic Retries - Built-in rate limiting and retries

Environment Variables

Required

FIRECRAWL_API_KEY - Your Firecrawl API key

Optional

FIRECRAWL_API_URL - Custom API endpoint for self-hosted
FIRECRAWL_RETRY_MAX_ATTEMPTS - Max retry attempts (default: 3)
FIRECRAWL_RETRY_INITIAL_DELAY - Initial retry delay in ms (default: 1000)

Usage Examples

Scrape the content from https://example.com

Search for the latest AI news and extract the content

Extract product information from these e-commerce URLs