Firecrawl's official MCP server lets agents scrape pages to markdown or structured data, search the web, map and crawl sites, interact with pages, parse documents and monitor changes. A hosted server supports keyless, OAuth or API-key access, and a local npx version is available.
Also available as
Connect
- 1Connect it in ChatGPT
Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.firecrawl.dev/v2/mcp as the MCP server URL. Add it to a chat from the composer's tools menu.
- 2Or add it to Codex or the API
codex mcp add firecrawl --url https://mcp.firecrawl.dev/v2/mcp --bearer-token-env-var FIRECRAWL_API_KEY
Configs are generated from the publisher's documented endpoint. Check their docs for plan requirements and scopes. New to this? Read the step-by-step tutorial.
Tools 11
firecrawl_scrapefirecrawl_searchfirecrawl_mapfirecrawl_crawlfirecrawl_check_crawl_statusfirecrawl_agentfirecrawl_interactfirecrawl_parsefirecrawl_developer_searchfirecrawl_monitor_runfirecrawl_credit_usageThings to ask
- “Scrape https://example.com/pricing into markdown”
- “Crawl the docs site and list all API endpoints”
- “Search the web for recent reviews of the Framework Laptop”
- “Monitor this page and tell me when the price changes”