Firecrawl turns any URL into clean markdown or structured JSON: one page, a whole site, or search results with their content. It handles JavaScript-heavy pages and pages that block simple scrapers. The official MCP server has a hosted endpoint, so there is nothing to run yourself.
In Claude Code or claude.ai, it's the fastest way to do competitor research, a content audit or a messaging comparison without copying pages by hand. In your own product, attach the hosted URL and your agent can check rivals' pricing pages every week, learn a customer's docs site on signup or extract product specs into JSON. To find pages first, pair it with Exa.
A real run
We asked it to compare the pricing pages of Linear, Asana and ClickUp. Four scrapes later Claude had the prices, the one limit each uses to force an upgrade, and seven ideas for a better pricing page.
Alternatives
| MCP | Pick it when | Popularity |
|---|---|---|
| You want a free, open-source crawler you run yourself | 85K ★, open source | |
| You read single pages as clean text and want a generous free tier | 0.9K ★, official | |
| You describe the data you want in plain words and get JSON back | Official | |
| You want search and page extraction from the same server | 2.4K ★, official |
Watch out
- A crawl can flood the model's context. Set a page
limitand depth.
- JSON extraction costs 5 credits per page instead of 1.
- Scraped pages can carry instructions aimed at your agent. Keep write tools behind human approval.
Install
In Claude Code:
Terminal
Loading editor...
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp
Without a key you get scraping and search with rate limits. Crawls need a key: add
--header "Authorization: Bearer YOUR_FIRECRAWL_API_KEY". The free plan has 1,000 credits a month, then plans start at $16 a month.In your product, attach the hosted URL
https://mcp.firecrawl.dev/v2/mcp with your key as the Bearer token (Claude API authorization_token or an AI SDK Authorization header). Never put the key in the URL.More in Top MCP servers for web data.
