Google Search Mcp

Google Search MCP Server

An MCP (Model Context Protocol) server that performs comprehensive web searches using Google Custom Search JSON API with advanced content extraction using Mozilla's Readability algorithm.

Features

• Three Search Modes:
• google_search - Fast snippet-only search for quick lookups
• deep_search - Full content extraction with Readability algorithm
• deep_search_news - News-optimized deep search
• Google Custom Search API - Uses official Google Custom Search JSON API
• Advanced Content Extraction - Uses Mozilla's Readability algorithm (same as Firefox Reader View) for clean article extraction
• Multiple Search Types - Web search, news search, and image search
• Domain Filtering - Include or exclude specific domains from results
• Retry Logic - Automatic retries with exponential backoff for reliability
• Controlled Concurrency - Fetches pages in batches to avoid overwhelming servers

Prerequisites

Get Google Custom Search API Credentials

1. Go to Google Cloud Console
2. Create a new project or select an existing one
3. Enable the "Custom Search API"
4. Go to "Credentials" and create an API key
5. Go to Programmable Search Engine
6. Create a new search engine and get your Search Engine ID (CX)

You'll need:

• GOOGLE_API_KEY - Your Google Cloud API key
• GOOGLE_CX - Your Programmable Search Engine ID

Installation

Using npx (Recommended)

No installation needed - just configure your MCP client:

{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": ["-y", "@thejusdutt/google-search-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "GOOGLE_CX": "your-search-engine-id"
      }
    }
  }
}

Global Installation

npm install -g @thejusdutt/google-search-mcp

Then configure:

{
  "mcpServers": {
    "google-search": {
      "command": "google-search-mcp",
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "GOOGLE_CX": "your-search-engine-id"
      }
    }
  }
}

Tools

google_search

Simple Google search for quick lookups. Returns snippets only without fetching full page content.

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | query | string | required | The search query | | num_results | number | 10 | Number of results (1-10) |

Example:

// Quick search with snippets only
google_search({ query: "React hooks tutorial" })

deep_search

Comprehensive web search with full content extraction.

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | query | string | required | The search query | | num_results | number | 10 | Number of results (1-10) | | max_content_per_page | number | 50000 | Max characters per page (5000-100000) | | search_type | string | "web" | Search type: "web", "news", or "images" | | include_domains | string | - | Comma-separated domains to include | | exclude_domains | string | - | Comma-separated domains to exclude |

Examples:

// Basic web search
deep_search({ query: "React best practices 2025" })

// News search
deep_search({ query: "AI announcements", search_type: "news" })

// Search specific sites only
deep_search({ 
  query: "TypeScript tips",
  include_domains: "github.com,dev.to"
})

// Exclude certain sites
deep_search({
  query: "web development trends",
  exclude_domains: "pinterest.com,facebook.com"
})

deep_search_news

Convenience wrapper for news search. Equivalent to calling deep_search with search_type: "news" and optimized content limits.

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | query | string | required | The news topic to search | | num_results | number | 10 | Number of articles (1-10) | | max_content_per_page | number | 30000 | Max characters per article |

Example:

deep_search_news({ query: "OpenAI latest updates" })

Configuration

Kiro

Add to ~/.kiro/settings/mcp.json:

{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": ["-y", "@thejusdutt/google-search-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "GOOGLE_CX": "your-search-engine-id"
      }
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": ["-y", "@thejusdutt/google-search-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "GOOGLE_CX": "your-search-engine-id"
      }
    }
  }
}

How It Works

1. Search - Queries Google Custom Search API to get top results
2. Fetch - Downloads each result page with retry logic
3. Extract - Uses Mozilla Readability to extract clean article content
4. Format - Returns consolidated markdown with full content from each page

Requirements

• Node.js 18+
• Google Cloud API key with Custom Search API enabled
• Programmable Search Engine ID (CX)

License

MIT

Author

thejusdutt

Contributing

Issues and PRs welcome at GitHub

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: thejusdutt
• Source: thejusdutt/google-search-mcp
• License: MIT

Install and usage instructions live in the source repository linked above.