Scrape Do MCP Server

MCP Server for Scrape.do - scraping, Google Search, Amazon, Async API, and Proxy Mode helpers

Local serverstdio

What is the Scrape Do MCP MCP server?

MCP Server for Scrape.do - scraping, Google Search, Amazon, Async API, and Proxy Mode helpers. That is what the scrape do mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

An MCP server that wraps Scrape.do's documented APIs in one package: the main scraping API, Google Search API, Amazon Scraper API, Async API, and a Proxy Mode configuration helper.

Getting it running

npm on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 13 tools. What each one is for:

  • scrape_url — Main Scrape.do scraping API wrapper
  • google_search — Structured Google search results
  • amazon_product — Amazon PDP structured data
  • amazon_offer_listing — Amazon seller offers
  • amazon_search — Amazon keyword/category results
  • amazon_raw_html — Raw Amazon HTML with geo-targeting
  • async_create_job — Create Async API jobs
  • async_get_job — Fetch Async job details
  • async_get_task — Fetch Async task details
  • async_list_jobs — List Async jobs
  • async_cancel_job — Cancel Async jobs
  • async_get_account — Fetch Async account/concurrency info

What it needs from you

Configuration is passed through the environment: SCRAPE_DO_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Scrape Do MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

This sits in the search and retrieval group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Scrape Do MCP's toolset — scrape_url, google_search, amazon_product and 10 more — is a fair guide to whether it matches your workflow. It is maintained by dztabel-happy; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
scrape_urlMain Scrape.do scraping API wrapper
google_searchStructured Google search results
amazon_productAmazon PDP structured data
amazon_offer_listingAmazon seller offers
amazon_searchAmazon keyword/category results
amazon_raw_htmlRaw Amazon HTML with geo-targeting
async_create_jobCreate Async API jobs
async_get_jobFetch Async job details
async_get_taskFetch Async task details
async_list_jobsList Async jobs
async_cancel_jobCancel Async jobs
async_get_accountFetch Async account/concurrency info
proxy_mode_configGenerate Proxy Mode configuration

How to install the Scrape Do MCP MCP server

{
  "mcpServers": {
    "scrape-do": {
      "command": "npx",
      "args": ["-y", "npm"],
      "env": {
        "SCRAPE_DO_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
SCRAPE_DO_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Scrape Do MCP to scrape url.
  • Use Scrape Do MCP to google search.
  • Use Scrape Do MCP to amazon product.

Frequently asked questions

It connects Scrape Do MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (scrape_url, google_search, amazon_product, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Scrape Do MCP directly.