firecrawl-mcp-server

MCP.Pizza Chef: firecrawl

Firecrawl reads live websites on your assistant's behalf — one page, every page under a section of a site, or a fresh web search — and hands back clean readable text. It can click and move through pages that need it, dig through a topic on its own, and search an index built for coding questions covering GitHub issues, pull requests, and documentation. Point your app at the hosted address to start; scraping, searching, and page interaction work without a key.

Data
Web/Research

Use This MCP server To

Pull the full text of an article into my chat Search the web and get the real page content back Collect every page in a documentation site at once Compare details across several product pages Research a topic across many sources in one go Read a page that only loads once its scripts run

README

Firecrawl MCP Server

A Model Context Protocol (MCP) server implementation that integrates with Firecrawl for web scraping capabilities.

Big thanks to @vrknetha, @cawstudios for the initial implementation!

Features

  • Scrape, crawl, search, extract, deep research and batch scrape support
  • Web scraping with JS rendering
  • URL discovery and crawling
  • Web search with content extraction
  • Automatic retries with exponential backoff
    • Efficient batch processing with built-in rate limiting
  • Credit usage monitoring for cloud API
  • Comprehensive logging system
  • Support for cloud and self-hosted Firecrawl instances
  • Mobile/Desktop viewport support
  • Smart content filtering with tag inclusion/exclusion
  • SSE Support

Play around with our MCP Server on MCP.so's playground or on Klavis AI.

Installation

Running with npx

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

Manual Installation

npm install -g firecrawl-mcp

Running on Cursor

Configuring Cursor šŸ–„ļø Note: Requires Cursor version 0.45.6+ For the most up-to-date configuration instructions, please refer to the official Cursor documentation on configuring MCP servers: Cursor MCP Server Configuration Guide

To configure Firecrawl MCP in Cursor v0.45.6

  1. Open Cursor Settings
  2. Go to Features > MCP Servers
  3. Click "+ Add New MCP Server"
  4. Enter the following:
    • Name: "firecrawl-mcp" (or your preferred name)
    • Type: "command"
    • Command: env FIRECRAWL_API_KEY=your-api-key npx -y firecrawl-mcp

To configure Firecrawl MCP in Cursor v0.48.6

firecrawl-mcp-server FAQ

Which apps does it work with?
Cursor, Claude Desktop, VS Code, and Windsurf all have documented setups, and any MCP client can use the hosted address.
Do I need a key?
Not to start — the hosted free tier allows scraping, searching, and page interaction. Crawling whole sites and extraction need a Firecrawl key.
How hard is setup?
Paste the hosted server address into your app, or add a short block with your key if you prefer running it locally.
Can I use this to summarize a long web page?
Yes — it fetches the page and returns readable text your assistant can then summarize.
Can it handle many pages at once?
Yes — it works through batches with rate limiting and automatic retries when a page fails.
Can I run it on my own servers?
Yes — it supports a self-hosted Firecrawl instance as well as the cloud service.