Active

firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Curs

The Firecrawl MCP Server lets your AI crawl entire sites, convert pages to clean Markdown, and run web searches — no manual copy-paste of page content.

For example, "scrape this competitor's pricing page and turn it into a comparison table" — the AI uses Firecrawl to fetch, parse, and return structured results. This is Firecrawl's official server.

GitHub ↗npm ↗
73
TrustScore
✅ No clear abandonment signal detected; complete security and compatibility checks before production use

What it does for you

Lets your AI crawl a whole site or page into clean Markdown — great for bulk-scraping static content and feeding knowledge bases.

Capabilities

  • Scrape a single page to clean Markdown
  • Crawl an entire site / many pages
  • Structured extraction from pages

Once installed, try asking your AI

Say this directly in Claude / Cursor or any client with this server connected

  • Crawl this docs site and compile everything into one Markdown file
  • Scrape the titles and summaries of the latest 10 posts from this blog

Why use it

Good for: developers and operators doing competitive research, content aggregation, or feeding real-time web data to the AI.

Officially maintained, high star count, top-tier TrustScore — full health data is shown below.

Before you connect

🔑 Needs an API key / tokenNode.js

Config example (to connect)

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

Works with these clients

  • Claude Desktopnpx
  • Claude Codenpx
  • Cursornpx
  • VS Codenpx
  • Windsurfnpx

Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.

Install / Connect

claude mcp add firecrawl-mcp -- npx -y firecrawl-mcp

Follow the official README; env and args vary per server.

🛠️ Maintenance weight 30% · 80 pts

📝
Last commit2 days ago
📈
Commits in 90 days100
💬
Recent issues with replies0%
🗃️
Repo statusNormal

📊 Adoption weight 25% · 79 pts

GitHub stars7.3k (90d +0%)
📦
npm weekly downloads91.1k(+0%)
🚀
Releases per month6.5

✅ Usability weight 20% · 55 pts

📋
Official registryNot listed
▶️
Runnable entryResolvable (npx/remote)
🔍
AuditabilityOpen-source repo, auditable

❤️ Health & community weight 25% · 73 pts

🐛
open issues154
🔀
open PRs
⚖️
LicenseMIT
👥
Contributors / forks28 / 855

Sources: GitHub API · npm registry · updated 2026-08-19

90-day trend

⭐ stars +0%

📦 weekly downloads +0%

Frequently Asked Questions

Can Firecrawl scrape pages behind a login?

It mainly scrapes publicly accessible pages; authenticated cases depend on configuration, and you should respect the target site's terms.

Does it cost money?

The server is open-source, but the Firecrawl scraping service it calls may have quota/paid tiers depending on your usage.

Similar / alternative servers

How to choose among these

Browser servers differ mainly on local vs. cloud, and whether you need to handle login / dynamic pages.

  • Operate login-gated, JS-rendered sitesPick Playwright MCP — a real browser with the fullest interaction
  • Bulk-scrape static sites to Markdown / feed a knowledge basePick Firecrawl — easiest for whole-site crawl and extraction
  • Want scaled, cloud-hosted browsersPick Browserbase / Hyperbrowser — cloud sessions

One email a week, 5 minutes to see what happened in the MCP ecosystem

New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.

One email a week · unsubscribe anytime · no data selling