MCP server
MCP
https://api.crawl4ai.com/mcpUse Crawl4AI as native tools inside ChatGPT, Claude, Cursor or any MCP client. No install: paste the URL and sign in, or add your key.
# sign in, no key # ChatGPT: Settings → Plugins / Apps → add a custom connector # Claude: Settings → Connectors → Add custom connector URL: https://api.crawl4ai.com/mcp # sign in with your Crawl4AI account and click Allow: the app runs on your own credits, # shows as a key named after the app in your dashboard, and you can revoke it there
# one line in your terminal claude mcp add --transport http crawl4ai \ https://api.crawl4ai.com/mcp \ --header "Authorization: Bearer sk_live_..."
# ~/.codex/config.toml [mcp_servers.crawl4ai] url = "https://api.crawl4ai.com/mcp" http_headers = { Authorization = "Bearer sk_live_..." }
# opencode.json { "mcp": { "crawl4ai": { "type": "remote", "url": "https://api.crawl4ai.com/mcp", "headers": { "Authorization": "Bearer sk_live_..." } } } }
# ~/.cursor/mcp.json (Windsurf: ~/.codeium/windsurf/mcp_config.json) { "mcpServers": { "crawl4ai": { "url": "https://api.crawl4ai.com/mcp", "headers": { "Authorization": "Bearer sk_live_..." } } } }
# ~/.openclaw/openclaw.json, the mcp.servers block { mcp: { servers: { crawl4ai: { url: "https://api.crawl4ai.com/mcp", transport: "streamable-http", headers: { Authorization: "Bearer sk_live_..." } } } } }
# Claude Desktop → Settings → Connectors → Add custom connector Name: crawl4ai URL: https://api.crawl4ai.com/mcp # then sign in with your Crawl4AI account and click Allow: no key needed
Note
Tools exposed: scrape · search · serp · answer · extract · batch · jobs_submit · jobs_status · jobs_results (the bulk jobs, 50 to 500 URLs) · recipes_list · recipe_run (the recipes) · the billing tools balance · plans · estimate · topup · spend_cap · recharge · and report_issue (sends a bug report to the Crawl4AI team). Your dashboard's MCP tab pre-fills this with your key.
Something unclear or wrong on this page? Tell us.