Firecrawl MCP: search, scrape and crawl from your AI app

Connect Firecrawl to Claude, ChatGPT or Cursor

1. 1Click Connect Firecrawl free and paste an API key from your Firecrawl account.
2. 2A single scrape or search is small; a full crawl can follow many pages. Switch off crawling if your AI app should stick to one URL at a time.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask Claude Code to scrape a library's docs page before it writes code against it, then open Activity to see the scrape.

What Firecrawl fetches for your AI app

• Search the web and get content from the top results in one call.
• Scrape a page, optionally after browser actions, or extract structured JSON with a prompt or schema.
• Map a site to discover its URLs, then crawl it with filters and track or cancel the job.
• Search research papers through Firecrawl's own MCP server, under Ways to connect.

Watch what gets fetched

• Switch off the crawl tools and keep search and single-page scraping.
• Policies check every call, so a token in a request can be blocked before Firecrawl fetches anything.
• Activity lists every search, scrape and crawl your team's AI apps ran.

ContextGate sees only calls that go through it, so an AI app's own built-in web search isn't recorded.

What you get with Firecrawl and ContextGate

• Your AI apps can use FirecrawlClaude, Cursor, ChatGPT and other AI apps reach Firecrawl through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Firecrawl tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Firecrawl tools

Examples of what your AI apps can do in Firecrawl. You'll see the exact list of tools after you connect it.

• Cancel a crawl jobCancels an active or queued web crawl job using its id; attempting to cancel completed, failed, or previously canceled jobs will not change their state.
• Get the status of a crawl jobRetrieves the current status, progress, and details of a web crawl job, using the job id obtained when the crawl was initiated.
• Map multiple URLsMaps a website by discovering urls from a starting base url, with options to customize the crawl via search query, subdomain inclusion, sitemap handling, and result limits; search effectiveness is sit
• Start a web crawlInitiates a firecrawl web crawl from a given url, applying various filtering and content extraction rules, and polls until the job is complete; ensure the url is accessible and any regex patterns for
• Extract structured dataExtracts structured data from web pages by initiating an extraction job and polling for completion; requires a natural language `prompt` or a json `schema` (one must be provided).
• Scrape URLScrapes a publicly accessible url, optionally performing pre-scrape browser actions or extracting structured json using an llm, to retrieve content in specified formats.
• SearchPerforms a web search for a query, scrapes content from the top search results using firecrawl, and returns details in specified formats.