Scrape a URL

Scrape a URL

Returns one page as clean markdown, HTML, links or a screenshot, or as JSON fields extracted with a prompt or schema.

Set up

Use the first option your agent supports.

MCP (official, remote)

Add this server to your agent's MCP settings, then sign in when asked.

{ "mcpServers": { "firecrawl": { "url": "https://mcp.firecrawl.dev/v2/mcp-oauth" } } }

Call the MCP tool firecrawl_scrape.

Server URL: https://mcp.firecrawl.dev/v2/mcp-oauth

CLI (official)

Install the command, then confirm it runs.

npm install -g firecrawl-cli
firecrawl --version

Run firecrawl scrape.

Set $FIRECRAWL_API_KEY in your environment first (get a key: https://www.firecrawl.dev/app/api-keys).

API (official)

• Base URL: https://api.firecrawl.dev/v2
• Endpoint: POST /scrape
• Auth: send the header Authorization: Bearer $FIRECRAWL_API_KEY
• Get a key: https://www.firecrawl.dev/app/api-keys
• Docs: https://docs.firecrawl.dev/api-reference/introduction

Before anything else, confirm access with the cheapest read-only call, like a list or a search. Never send or change anything to test access.

Rules

• Ask the user before anything that sends messages, costs money, or changes data, and say how many records it touches. One approval covers a batch the user has seen.
• Never print API keys.