TL;DR

Firecrawl is a Web Scraping MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent extract clean data from any website. Install in 1 minute with mcpizy install firecrawl.

🔥

Firecrawl

Install verified 5 tools

Web Scraping

Last updated September 4, 2026 · By MCPizy team

Extract clean data from any website. Turn entire websites into LLM-ready markdown or structured data.

Official homepage

Repo audit: 100/100 — actively maintained, documented and licensed

Scored on licence, adoption, maintenance and documentation of mendableai/firecrawl-mcp-server. We show the grade whether it flatters the server or not.

last commit 2 days ago · 7,307 stars · MIT licence · 156 open issues

Read the full audit on CheckMCP

Install Firecrawl

Via MCPizy CLI (recommended):

mcpizy install firecrawl

Or run directly:

npx -y firecrawl-mcp

View on GitHub

Tools exposed

5 tools available

firecrawl_scrape

Scrape a single URL and return markdown + metadata

Inputs

urlstringrequired
formatsstring[]optional

firecrawl_crawl

Crawl a website recursively up to a depth

Inputs

urlstringrequired
limitnumberoptional

firecrawl_map

Map all URLs on a website

Inputs

urlstringrequired

firecrawl_search

Search the web and scrape top results

Inputs

querystringrequired
limitnumberoptional

firecrawl_extract

Extract structured data using a schema

Inputs

urlsstring[]required
schemaobjectrequired

Configuration

Works identically across clients. Only the config file path differs.

Claude Code~/.claude.json

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

Cursor.cursor/mcp.json

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

Windsurf~/.codeium/windsurf/mcp_config.json

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

Authentication setup

1
Create an API key in the Firecrawl dashboard
Get it FIRECRAWL_API_KEY

What you can do with Firecrawl MCP

Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.

“Scrape https://news.ycombinator.com and give me the top 10 headlines”

Uses: firecrawl_scrape

“Crawl anthropic.com and build a sitemap of docs pages”

Uses: firecrawl_crawl, firecrawl_map

“Extract product name, price, and rating from these 20 Amazon pages”

Uses: firecrawl_extract

“Search the web for 'MCP server best practices 2025' and summarise”

Uses: firecrawl_search

Works with

Claude Code

Claude Desktop

Cursor

Windsurf

VS Code + Copilot

Any MCP Client

More Web Scraping MCPs

📸

ScreenshotOne

Render high-quality website screenshots. Full page captures, element selection, and custom viewports.

🕷️

Crawlbase

Real-time web data extraction with HTML, markdown, and screenshot support.

🔗

Decodo

Easy web data access and simplified information retrieval with proxy support.

🌐

Scrapeless

Real-time Google SERP results integration for LLM applications.

Alternatives to Firecrawl

If Firecrawl doesn't fit your stack, these Web Scraping MCP servers solve similar problems.

💡

Bright Data

Extract and interact with the web at scale. Automated access with proxy networks and SERP API.

🦎

Oxylabs

Scrape websites with Oxylabs Web API. Dynamic rendering, SERP data, and e-commerce extraction.

🤖

Apify

Use 3,000+ pre-built cloud tools to extract data from websites, social media, and e-commerce platforms.

Frequently asked questions

What is the Firecrawl MCP server?

Firecrawl is listed as an Web Scraping Model Context Protocol server whose documented purpose is to let an MCP-compatible agent extract clean data from any website. Client support, permissions and authentication remain specific to the upstream project.

How do I install Firecrawl MCP with Claude Code?

The fastest way is the MCPizy CLI: run `mcpizy install firecrawl` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y firecrawl-mcp` and restarting Claude Code.

Does MCPizy charge to view or install Firecrawl MCP?

No. Reading this profile and copying its install guidance is free. Upstream software, API, account or usage costs are separate, and licence coverage should be checked from the linked source when available.

Does Firecrawl MCP work with Cursor and Windsurf?

The MCP standard is supported by those clients, but a specific server can still have client-specific setup or transport limits. Use the configuration shown on this page when present and verify the upstream instructions before installation.

What can I do with Firecrawl MCP?

Its documented purpose is to let an MCP-compatible agent extract clean data from any website. The exact tools, permissions and write capabilities depend on the server version and configuration shown by the upstream project.

Compare before you commit

Put this server beside an alternative, or return to the full evidence directory.

Compare MCP servers Back to directory