Scrapingdog MCP Server

Scrapingdog MCP Server

A Model Context Protocol server that exposes the Scrapingdog web-scraping and SERP APIs as tools any MCP-compatible client (Claude Desktop, Claude Code, Cursor, etc.) can call.

One tool per Scrapingdog product — general web scraping, the full Google family, Amazon, Walmart, eBay, LinkedIn, X, YouTube, Bing, Baidu, and screenshots.

Requirements

• Node.js ≥ 18
• A Scrapingdog API key — get one on your dashboard.

Install & build

npm install
npm run build

Configuration

The server reads your API key from the SCRAPINGDOG_API_KEY environment variable. It is never passed as a tool argument, so it stays out of the model's context, transcripts, and logs.

Claude Desktop

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "scrapingdog": {
      "command": "node",
      "args": ["/absolute/path/to/ScrapingdogMCP/dist/index.js"],
      "env": {
        "SCRAPINGDOG_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude Code

claude mcp add scrapingdog -e SCRAPINGDOG_API_KEY=your_api_key_here -- node /absolute/path/to/ScrapingdogMCP/dist/index.js

Available tools

35 tools. Each tool's full parameter set (with descriptions and API defaults) is generated from src/endpoints.ts and surfaced to the client as the tool's input schema. All paths were validated against the live API except amazon_reviews (⚠️) — see Known issues.

General

Google family

E-commerce

Social / professional

Other search engines

AI / LLM & tools

Known issues

All 35 endpoints were validated against the live API and return data, with one exception:

• amazon_reviews — the /amazon/reviews route is correct, but the live endpoint currently responds HTTP 400 "Something went wrong" for every input (any ASIN, with or without extra params). This looks like a Scrapingdog backend/plan-scope issue rather than a wrapper bug. It stays marked with verify: true in src/endpoints.ts until it returns data. List flagged endpoints anytime with:

npm run list:unverified

Adding or adjusting an endpoint

Every endpoint is a single declarative object in src/endpoints.ts — no handler code to write. To add a Scrapingdog product (e.g. Google Hotels, Patents, TikTok), append:

{
  tool: "google_hotels",
  title: "Google Hotels API",
  path: "/google_hotels",
  description: "…",
  params: [
    { name: "query", type: "string", required: true, description: "…" },
    // …
  ],
}

Rebuild with npm run build.

Architecture

src/
  types.ts       Endpoint / EndpointParam type definitions
  endpoints.ts   Declarative registry of every Scrapingdog API
  client.ts      HTTP client: URL building, API-key resolution, error handling
  server.ts      Compiles each endpoint into an MCP tool + Zod input schema
  index.ts       stdio entry point

License

MIT