home / mcp / firecrawl mcp server

Firecrawl MCP Server

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "0xzapata-firecrawl-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You run a Firecrawl MCP Server to enable powerful web scraping, crawling, and data extraction capabilities for your projects. It integrates Firecrawl’s APIs with your MCP client so you can discover, scrape, map, search, and analyze web content in a scalable way from your chosen development environment.

How to use

You connect to the Firecrawl MCP Server from your MCP client to perform a range of web tasks. Start by configuring your MCP client to point at the local or cloud-enabled server, then choose the appropriate tool for your goal. For discovery and extraction you can map a site to find URLs, scrape a single page, batch-scrape known pages, or run full crawls for comprehensive coverage. For research and data extraction, you can use deep_research or extract with a defined schema. When you describe your scraping needs in your MCP client, the server handles retries, rate limiting, and credit monitoring automatically.

How to install

Prerequisites: Node.js and npm installed on your machine.

Install and run the MCP server using the recommended approach for quick setup.

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

If you prefer a global installation, install the MCP server package and run it with Node.js as shown.

npm install -g firecrawl-mcp

Running on Cursor and Windsurf (examples)

Cursor and Windsurf provide integrated ways to configure MCP servers inside those environments. The code blocks below show how to register the Firecrawl MCP server in each tool. Use the exact commands and environment variables as shown.

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

On Windsurf, add this to your model config to run the MCP server with the API key.

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

Running with SSE Local Mode

To run the server using Server-Sent Events (SSE) locally instead of the standard stdio transport, enable SSE_LOCAL.

env SSE_LOCAL=true FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
```
Use the url: http://localhost:3000/sse

Available tools

firecrawl_scrape

Scrape content from a single URL with advanced options for formats, content scope, and timeouts.

firecrawl_batch_scrape

Scrape multiple known URLs efficiently with built-in rate limiting and parallel processing.

firecrawl_map

Discover all indexed URLs on a site to plan scraping scope.

firecrawl_search

Search the web for information and optionally extract content from results.

firecrawl_crawl

Start an asynchronous crawl of a site to extract content from multiple pages with depth and limit controls.

firecrawl_extract

Extract structured data from pages using LLM capabilities, with optional schemas.

firecrawl_deep_research

Conduct multi-source, in-depth research with intelligent crawling and analysis.

firecrawl_generate_llmstxt

Generate a standardized llms.txt file for a domain to guide AI interaction.