Firecrawl MCP Server

✓ verified

Scrape, crawl, and extract structured data from websites.

Don't have ToolPiper? We'll take you to the download.

Open repository →

Publisher

Firecrawl

License

MIT

Transport

Local subprocess

Tools

5

What this server does

Firecrawl turns websites into clean markdown or structured JSON. Scrape one page, crawl a whole site, map every URL, or pass a schema and have it extract typed fields from across many pages. It handles JavaScript-rendered pages and pagination, which is where naive fetchers fail. Useful for building a grounding corpus, monitoring a competitor's docs, or pulling product data into a spreadsheet.

Tools included

  • firecrawl_scrape

    Scrape a single URL and return markdown or structured data.

  • firecrawl_crawl

    Crawl a site and return content from every page.

  • firecrawl_map

    Discover all URLs on a site.

  • firecrawl_extract

    Extract structured fields from pages using a schema.

  • firecrawl_search

    Search the web and scrape the results.

The authoritative list comes from the server's tools/list at runtime. This catalog entry may lag the upstream until the next ToolPiper release.

Install in ToolPiper

ToolPiper handles the JSON configuration. Click Install, fill in any required tokens, and the server is ready in your chat.

Don't have ToolPiper? We'll take you to the download.

Install in another client

Install in another MCP client (Claude Desktop, Cursor, Continue, Cline)

Add this to ~/Library/Application Support/Claude/claude_desktop_config.json.

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ]
    }
  }
}

Example prompts

  • "Scrape the pricing page at example.com and return it as markdown."

  • "Crawl docs.example.com and give me every page under the API reference."

  • "Extract product name, price, and SKU from each item page on this store."

Security notes

The API key gates billing on the hosted Firecrawl API. Treat it as a credential and rotate it if it leaks. Crawls can consume a lot of credits quickly, so scope them with limits. Scraped content is untrusted; do not let the model follow instructions embedded in fetched pages.

Related tools