Serper Search and Scrape MCP Server

@marcopesani

About Serper Search and Scrape MCP Server

Serper MCP Server supporting search and webpage scraping

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-serper": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@marcopesani/mcp-server-serper",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

Perform web searches via Serper API

Extract content from web pages

Overview

What is Serper Search and Scrape MCP Server?

A TypeScript-based MCP server that provides web search and webpage scraping capabilities using the Serper API. It integrates with Claude Desktop to enable powerful web search and content extraction features.

How to use Serper Search and Scrape MCP Server?

Install via Smithery, Claude Desktop, Cline, Cursor, or Docker. Set the SERPER_API_KEY environment variable with your Serper API key, then use the provided google_search and scrape tools through an MCP client.

Key features of Serper Search and Scrape MCP Server

google_search tool for web searches via Serper API
Rich search results including knowledge graph and "people also ask"
Supports region, language, location, pagination, time filters, and autocorrection
Advanced search operators like site:, filetype:, inurl:, intitle:, related:, cache:, date filters, exact phrase, exclude, and OR
scrape tool extracts page content as plain text and optional markdown
Includes JSON-LD, head metadata, and preserves document structure

Use cases of Serper Search and Scrape MCP Server

Perform web searches from within Claude Desktop
Extract structured content from web pages for analysis
Use advanced search operators to filter and refine search results
Integrate web search and scraping into AI‑assisted workflows

FAQ from Serper Search and Scrape MCP Server

What are the runtime requirements?

Node.js >= 18 and a Serper API key set as the SERPER_API_KEY environment variable.

How do I install and configure the server?

You can install it via Smithery (npx @smithery/cli install ...), or add it manually to your MCP client configuration (Claude Desktop, Cline, Cursor) using npx -y serper-search-scrape-mcp-server with the API key. A Docker build option is also available.

What tools does the server provide?

Two tools: google_search (web search) and scrape (webpage content extraction).

How does authentication work?

Authentication is handled via your Serper API key, which must be provided as the SERPER_API_KEY environment variable.

Where is my data processed?

All search and scrape requests are made to the Serper API; data is processed by Serper's servers. The server itself runs locally and communicates over stdio.

Frequently asked questions

What are the runtime requirements?

Node.js >= 18 and a Serper API key set as the `SERPER_API_KEY` environment variable.

How do I install and configure the server?

You can install it via Smithery (`npx @smithery/cli install ...`), or add it manually to your MCP client configuration (Claude Desktop, Cline, Cursor) using `npx -y serper-search-scrape-mcp-server` with the API key. A Docker build option is also available.

What tools does the server provide?

Two tools: `google_search` (web search) and `scrape` (webpage content extraction).

How does authentication work?

Authentication is handled via your Serper API key, which must be provided as the `SERPER_API_KEY` environment variable.

Where is my data processed?

All search and scrape requests are made to the Serper API; data is processed by Serper's servers. The server itself runs locally and communicates over stdio.

Comments

Basic information

More Search MCP servers

Tavily Mcp

tavily-ai

Production ready MCP server with real-time search, extract, map & crawl.

2.2K

Google Search MCP Server

mixelpixx

MCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites

249

QuanticData — Web Scraping MCP Server

quantumproxies

Web scraping MCP server for AI agents: scrape any page to clean Markdown, SERP search (Google, Bing, DuckDuckGo), site crawl and map, 74 ready-made collectors and residential proxies. 25 tools, pay per success.

Baidu AI Search

baidubce

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

583

mcp-omnisearch

spences10

🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

332