📌Overview

Purpose: To provide powerful Google search capabilities and AI-driven deep research tools through the Serper API for MCP-enabled applications.

Overview: The Serper Search MCP Server integrates advanced Google search functionalities with a robust AI-powered research tool, allowing developers to enhance their applications with comprehensive search and iterative research capabilities.

Key Features:

• Powerful Google search integration: Utilizes the Serper API to fetch rich search data such as knowledge graph information, organic results, and related searches.

• AI-powered Deep Research tool: Conducts multi-step, iterative research that generates sub-queries, synthesizes information from various sources, provides citations, and allows customizable research depths.

---

Serper Search MCP Server

A Model Context Protocol server that provides Google search capabilities through the Serper API, along with an AI-powered Deep Research tool. This server enables easy integration of search and research functionality into your MCP-enabled applications.

✨ Features

• 🌐 Google search integration through Serper API
• 🔄 Rich search response data including:
  • Knowledge Graph information
  • Organic search results
  • "People Also Ask" questions
  • Related searches
• 🧠 AI-powered Deep Research tool:
  • Multi-step, iterative research
  • Generates sub-queries for thorough exploration
  • Synthesizes information from multiple sources
  • Provides citations for information
  • Adjustable research depth levels
  • Built-in quality metrics for improvement
• 🛠 Configurable search parameters:
  • Country targeting
  • Language selection
  • Result count customization
  • Autocorrect options
• 🔒 Secure API key handling
• ⚡️ Rate limiting and caching support
• 📝 TypeScript support with full type definitions
• 📊 Integrated performance metrics for optimization

🚀 Installation

1. Clone the repository:

git clone https://github.com/yourusername/serper-search-server.git
cd serper-search-server

2. Install dependencies:

pnpm install

3. Build the server:

pnpm run build

⚙️ Configuration

1. Get your Serper API key from https://serper.dev

2. Create a .env file in the root directory:

# Required
SERPER_API_KEY=your_api_key_here

# Optional - Advanced Quality Metrics Configuration (pre-configured by default)
USAGE_METRICS_KEY=your-custom-metrics-key     # Optional
USAGE_PROJECT_ID=your-custom-project-id       # Optional
METRICS_ENDPOINT=https://your-custom-host.com # Optional
DISABLE_METRICS=false                         # Not recommended

See TELEMETRY.md for detailed information about quality metrics collection, performance monitoring, usage analytics, dashboard setup, and continuous improvement.

🔌 Integration

Claude Desktop

Add the server config to your Claude Desktop configuration:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "serper-search-server": {
      "command": "/path/to/serper-search-server/build/index.js",
      "env": {
        "SERPER_API_KEY": "your_api_key_here"
      }
    }
  }
}

🛠 Usage

Search Tool

The server provides a search tool with these parameters:

{
  "query": string,          // Search query
  "numResults"?: number,    // Number of results (default: 10, max: 100)
  "gl"?: string,            // Country code (e.g., "us", "uk")
  "hl"?: string,            // Language code (e.g., "en", "es")
  "autocorrect"?: boolean,  // Enable autocorrect (default: true)
  "type"?: "search"         // Search type (more types coming soon)
}

Deep Research Tool

For comprehensive research, use the deep research tool with parameters:

{
  "query": string,                     // Research query or question
  "depth"?: "basic" | "standard" | "deep",  // Research depth (default: "standard")
  "maxSources"?: number                // Maximum sources to include (default: 10)
}

The deep research tool:

• Breaks down complex queries into sub-queries
• Executes multiple searches to gather information
• Uses AI to synthesize information from multiple sources
• Formats results with citations and references
• Adapts research based on intermediate results
• Collects anonymous quality metrics for improvement

Depth Levels:

• basic: Quick overview (3-5 sources, ~5 min)
  Good for simple facts and definitions
• standard: Comprehensive (5-10 sources, ~10 min)
  Balanced depth for most needs
• deep: Exhaustive (10+ sources, ~15-20 min)
  For complex topics and thorough analysis

Search Tool Example Response

Includes rich data such as knowledge graph, organic results, "people also ask," and related searches.

{
  "searchParameters": {
    "q": "apple inc",
    "gl": "us",
    "hl": "en",
    "autocorrect": true,
    "type": "search"
  },
  "knowledgeGraph": {
    "title": "Apple",
    "type": "Technology company",
    "website": "http://www.apple.com/",
    "description": "Apple Inc. is an American multinational technology company...",
    "attributes": {
      "Headquarters": "Cupertino, CA",
      "CEO": "Tim Cook (Aug 24, 2011–)",
      "Founded": "April 1, 1976, Los Altos, CA"
    }
  },
  "organic": [
    {
      "title": "Apple",
      "link": "https://www.apple.com/",
      "snippet": "Discover the innovative world of Apple...",
      "position": 1
    }
  ],
  "peopleAlsoAsk": [
    {
      "question": "What does Apple Inc mean?",
      "snippet": "Apple Inc., formerly Apple Computer, Inc....",
      "link": "https://www.britannica.com/topic/Apple-Inc"
    }
  ],
  "relatedSearches": [
    {
      "query": "Who invented the iPhone"
    }
  ]
}

🔍 Response Types

Knowledge Graph

• Title and type
• Website URL
• Description
• Key attributes

Organic Results

• Title and URL
• Snippet (description)
• Position in results
• Sitelinks when available

People Also Ask

• Question text
• Answer snippet
• Source link

Related Searches

• List of related queries

📊 Quality Metrics

The Deep Research tool includes integrated quality metrics:

• Research process metrics
• Performance monitoring
• Issue tracking
• Usage patterns
• Result quality indicators

See TELEMETRY.md for details about metrics collection and improving search quality.

🤝 Contributing

Contributions are welcome! Please submit a Pull Request.

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Serper API for Google search capabilities
• Model Context Protocol for the MCP framework
• PostHog for analytics capabilities