MCP Catalogs
Homefirecrawl-mcp-server screenshot

firecrawl-mcp-server

by firecrawl·6,317·Score 60

Official Firecrawl MCP Server brings web scraping, search, and page interaction capabilities to MCP-compatible AI agents.

web-scrapingdeveloper-toolsai-llm
724
Forks
115
Open issues
this month
Last commit
2d ago
Indexed

Overview

The Firecrawl MCP Server is a robust implementation that enables AI agents to search the web, scrape any URL into clean structured data, and interact with pages through clicking, navigation, and automation. It offers both cloud and self-hosted deployment options with automatic retries and rate limiting. The server supports SSE (Server-Sent Events) for real-time data streaming and provides multiple tools including scrape, batch_scrape, map, crawl, search, agent, and browser automation capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Web research for content analysis and information gathering
you:Automated data extraction from websites for business intelligence
you:Real-time web search capabilities integrated into AI conversations
you:What is required to use the Firecrawl MCP Server?
you:Can I use this server with different LLM clients?

When to choose this

When you need reliable web scraping, search, and interaction capabilities for your AI agent and are already using or willing to use Firecrawl's API.

When NOT to choose this

When you need self-contained scraping without external dependencies or when you're concerned about vendor lock-in with Firecrawl's API.

Tools this server exposes

8 tools extracted from the README
  • firecrawl_scrape

    Scrape content from a single URL with advanced options.

  • interact

    Interact with a scraped page (click, type, navigate).

  • batch_scrape

    Scrape multiple known URLs efficiently.

  • map

    Discover URLs on a site.

  • crawl

    Multi-page extraction from a site with limits.

  • search

    Web search for information.

  • agent

    Complex multi-source research with autonomous agent.

  • browser

    Interactive multi-step automation (deprecated).

Comparable tools

mcp-server-puppeteermcp-server-playwrightmcp-server-serpapi

Installation

Installation

Running with npx
env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
Manual Installation
npm install -g firecrawl-mcp
Claude Desktop Configuration

Add this to your claude_desktop_config.json:

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

FAQ

What is required to use the Firecrawl MCP Server?
You need a Firecrawl API key which can be obtained from https://www.firecrawl.dev/app/api-keys. For self-hosted instances, you can set FIRECRAWL_API_URL to your custom endpoint.
Can I use this server with different LLM clients?
Yes, the Firecrawl MCP Server is designed to work with any MCP-compatible AI clients including Cursor, Claude, and others. Configuration instructions are provided for multiple platforms.

Compare firecrawl-mcp-server with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.