Firecrawl

Add to your client

Copy the config for your MCP client and paste it into its config file.

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "<your-firecrawl-api-key>"
      }
    }
  }
}

Before you start

• Node.js (18+) with npx, or install globally via npm
• A Firecrawl API key (format fc-...) from https://www.firecrawl.dev/app/api-keys
• Optional: FIRECRAWL_API_URL to target a self-hosted Firecrawl instance instead of the cloud API

About Firecrawl

Tools & capabilities (8)

When to use it

• Use it when an LLM needs clean Markdown from a JavaScript-heavy page that a simple HTTP fetch can't render.
• Use it when you want to crawl an entire docs site or knowledge base into structured content for RAG.
• Use it when you need structured fields (prices, contacts, specs) pulled from pages against a JSON schema.
• Use it when you want web search results plus the actual page content in one step.
• Use it when mapping a site's URL structure before deciding what to scrape.
• Use it when you need anti-bot handling and automatic retries without writing scraping infrastructure yourself.

Quick setup

1. 1Get a Firecrawl API key from the Firecrawl dashboard (firecrawl.dev/app/api-keys).
2. 2Add the server to your MCP client config with command `npx -y firecrawl-mcp` and `FIRECRAWL_API_KEY` in the env block.
3. 3Optionally set FIRECRAWL_API_URL for a self-hosted instance, or retry/credit-warning env vars.
4. 4Restart the MCP client so it picks up the new server.
5. 5Verify by asking the model to scrape a URL and confirm it returns Markdown.

Firecrawl FAQ