Firecrawl MCP Server

Firecrawl's own MCP server brings Firecrawl, its context API for AI agents, into your agent. It searches the web, turns any page into clean Markdown or structured JSON, maps and crawls sites, works through pages in a real browser and runs research jobs across several sites. What you can do with it - Search the web, with the full content of the results when you need it - Scrape any URL into Markdown, or into JSON that matches a schema you give it - Map a site to find its URLs, or crawl a section for content from many pages - Parse PDFs, Word documents, spreadsheets and other files - Click, type, fill forms and navigate dynamic pages in a real browser - Run Agent jobs that research across several sites and return structured data - Monitor pages on a schedule and get told when their content changes - Search developer sources (GitHub issues, pull requests, READMEs and docs), US government sources, and scientific papers from PubMed, bioRxiv, medRxiv and arXiv - Check your Firecrawl credit usage How it connects Firecrawl hosts it at https://mcp.firecrawl.dev/v2/mcp. With no key, the keyless free tier lets you scrape, search and parse within daily limits. Add your Firecrawl API key as an Authorization: Bearer header to unlock every tool and your plan's limits, or point your agent at https://mcp.firecrawl.dev/v2/mcp-oauth to sign in to Firecrawl in your browser instead. Firecrawl also offers native connectors for ChatGPT, Codex and Claude. To run it yourself, use npx -y firecrawl-mcp with FIRECRAWL_API_KEY set. It also comes as a Docker image and a Gemini CLI extension, and it can use a self-hosted Firecrawl through FIRECRAWL_API_URL. Good to know - Set your API key in your agent's settings; never put it in the server address or a chat. - Crawl, map and Agent jobs need a key or sign-in; they aren't part of the keyless tier. - Calls use your team's Firecrawl credits. - A search-only address, https://mcp.firecrawl.dev/v2/mcp-search, offers just the search tools.

• “Get the product details from https://example.com/product.”

  1. firecrawl_scrape
  Copy

• “List all URLs on example.com.”

  1. firecrawl_map
  Copy

• “Compare remote work stipend policies across tech companies.”

  1. firecrawl_search
  Copy

• “Get all blog posts from the first two levels of example.com/blog.”

  1. firecrawl_crawl