For non-developers
What can Claude do with Firecrawl?
Imagine asking your AI: 'Crawl this documentation site and give me clean markdown for every page' — and it turns any website into structured, LLM-ready content. This server connects your AI to Firecrawl, which crawls websites and returns clean markdown or structured data, skipping ads and navigation cruft.
★ Hand-picked walkthrough
Firecrawl MCP = Effortless Web Scraping
Things you can ask Claude
Documentation Ingestion
Crawl a whole docs site and get clean markdown for each page.
Say to Claude
Crawl https://docs.example.com and return clean markdown for every page under /guides Structured Extraction
Pull specific structured data from pages with AI-assisted selectors.
Say to Claude
Extract product name, price, and description from all product pages on example-shop.com Content Refresh
Re-crawl a site to get updated content for RAG indexes.
Say to Claude
Re-crawl our help center and return only pages that changed since last week When it helps
- ✓You want to ingest a whole documentation site as AI context
- ✓You need clean markdown from sites that are messy HTML
- ✓You're building RAG and need bulk-cleaned content
- ✓You want structured extraction (pricing, products, team members) from a site
FAQ
Can Claude use Firecrawl?
Yes. With the Firecrawl MCP connector (an MCP server), Claude can work with Firecrawl directly in your conversation — Firecrawl web scraping server — AI-powered web crawling, content extraction, and structured data collection at scale.
Do I need to code to use Firecrawl with Claude?
No. You install the connector once (a short config or one command), then you just ask Claude in plain English. The example prompts on this page work as-is.
How do I add Firecrawl to Claude?
Open the Firecrawl connector page for copy-paste setup, or follow the per-client guide for Claude Desktop, Claude Code, Cursor, or ChatGPT.
Set up Firecrawl in Claude
Copy-paste config, setup steps, plus the walkthrough — on the connector page.