@scrapio/mcp

Official MCP server for Scrapio — gives AI agents direct access to fetch, crawl, search, and extract structured data from the web.

Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible agent runtime.

Install

No installation required. Run with npx:

SCRAPIO_API_KEY=sk-... npx @scrapio/mcp

Configure your agent

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "scrapio": {
      "command": "npx",
      "args": ["-y", "@scrapio/mcp"],
      "env": {
        "SCRAPIO_API_KEY": "sk-..."
      }
    }
  }
}

Restart Claude Desktop. The tools appear automatically.

Cursor

Open Cursor Settings → MCP and add a new server, or edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "scrapio": {
      "command": "npx",
      "args": ["-y", "@scrapio/mcp"],
      "env": {
        "SCRAPIO_API_KEY": "sk-..."
      }
    }
  }
}

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "scrapio": {
      "command": "npx",
      "args": ["-y", "@scrapio/mcp"],
      "env": {
        "SCRAPIO_API_KEY": "sk-..."
      }
    }
  }
}

HTTP transport (remote / self-hosted)

SCRAPIO_API_KEY=sk-... npx @scrapio/mcp --transport http --port 3010

The server listens on http://localhost:3010/mcp.

Available tools

| Tool | Description | |------|-------------| | fetch | Fetch a URL and return content as markdown, HTML, JSON, or screenshot | | google_search | Search Google and return structured organic, news, image, or shopping results | | fast_search | Lightweight organic + news search, priced below google_search | | interact | Drive a real browser — click, type, scroll, wait for elements | | crawl | Crawl one or more seed URLs and return content for every page visited | | submit_job | Submit a long-running job asynchronously and return a job ID | | get_job | Check job status and retrieve the result when complete | | amazon_product | Get structured product data from Amazon by URL, ASIN, or search query | | amazon_search | Search Amazon and return structured product listings | | amazon_search_crawl | Queue an async, multi-page Amazon search crawl — returns a job ID | | walmart_search | Search Walmart and return structured product listings | | walmart_search_crawl | Queue an async, multi-page Walmart search crawl — returns a job ID | | youtube_transcript | Get the full transcript for a YouTube video by URL or video ID | | youtube_search | Search YouTube and return structured video results | | youtube_video | Get structured metadata for a single YouTube video | | youtube_search_crawl | Queue an async, multi-page YouTube search crawl — returns a job ID | | booking_search | Search Booking.com for hotels by location and stay dates | | booking_property | Get amenities, room rates, and review score for a Booking.com property | | booking_reviews | Get guest reviews and the score breakdown for a Booking.com property | | agoda_search | Search Agoda for hotels by location and stay dates | | agoda_property | Get amenities, room rates, and review score for an Agoda property | | agoda_reviews | Get guest reviews and the score breakdown for an Agoda property |

Example prompts

"Fetch the content of https://news.ycombinator.com and summarize the top 5 stories."

"Search Google for 'best TypeScript ORM 2025' and give me the top 3 results."

"Get the transcript of this YouTube video: https://www.youtube.com/watch?v=dQw4w9WgXcQ"

"Find the current price of the Sony WH-1000XM5 headphones on Amazon."

"Crawl https://docs.example.com up to 20 pages and extract all the API endpoint descriptions."

"Search Booking.com for hotels in Lisbon, check-in Sept 10, check-out Sept 14, for 2 adults."

"Search Agoda for hotels in Bangkok under $100/night sorted by rating."

Environment variables

| Variable | Required | Description | |----------|----------|-------------| | SCRAPIO_API_KEY | Yes | Your API key. Get one at scrapio.dev | | SCRAPIO_BASE_URL | No | Override the API base URL (for local dev or staging) | | MCP_PORT | No | Port for HTTP transport. Defaults to 3010 |

Links

• Documentation
• Get an API key
• Dashboard

License

MIT