Get Agent Loadout
Build agentsIntermediateDocs-checked, not yet hands-on tested

Turn websites into clean data

Extract structured data from many pages without writing a scraper.

Starter prompt

Map <site>, then extract every <item> page into data/items.json with fields {name, url, price, updated}. Deduplicate, validate the JSON, and report pages that failed.

Config

.mcp.json

{
  "mcpServers": {
    "firecrawl-mcp": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": { "FIRECRAWL_API_KEY": "fc-YOUR_API_KEY" }
    }
  }
}

Setup steps

  1. Add the Firecrawl MCP.
  2. Try one page first.
  3. Scale to the full site.

Why this works

Firecrawl handles rendering and cleanup; the agent handles the schema.

Watch out

Check site terms before scraping.

Related loadouts

Compare the gear: Web search and scraping for agents tier list · AI coding agents tier list · AI code review tier list