The Serper Search MCP Server allows you to:
Perform Google searches via the Serper API with configurable parameters (country, language, result count, autocorrect)
Retrieve rich search results including knowledge graph information, organic results, related questions, and "People Also Ask" data
Conduct AI-powered deep research with adjustable depth levels (basic, standard, deep)
Generate synthesized research reports with citations from multiple sources
Leverage multi-step, iterative research capabilities with AI synthesis and sub-queries
Integrate easily into MCP-enabled applications with full TypeScript support
Provides Google search capabilities through the Serper API, including knowledge graph information, organic search results, related questions, and the ability to perform deep multi-step research with customizable parameters.
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
🌐 Powerful 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:
Performs multi-step, iterative research
Generates sub-queries to explore topics thoroughly
Synthesizes information from multiple sources
Provides citations for all information
Adjustable research depth levels
Built-in quality metrics for continuous 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 result optimization
🚀 Installation
Clone the repository:
Install dependencies:
Build the server:
⚙️ Configuration
Get your Serper API key from [Serper.dev](https://serper.de
Create a
.env
file in the root directory:
See TELEMETRY.md for detailed information about:
Quality metrics collection
Performance monitoring
Usage analytics
Dashboard setup
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
🛠 Usage
Search Tool
The server provides a powerful search tool with the following parameters:
Deep Research Tool
For more comprehensive research needs, the server provides a deep research tool that performs multi-step research with the following parameters:
The deep research tool:
Breaks down complex queries into focused sub-queries
Executes multiple searches to gather comprehensive information
Uses AI to synthesize information from multiple sources
Formats results with proper citations and references
Adapts its research strategy based on intermediate results
Collects anonymous quality metrics to improve search results
Depth Levels:
basic: Quick overview (3-5 sources, ~5 min) Good for: Simple facts, quick definitions, straightforward questions
standard: Comprehensive analysis (5-10 sources, ~10 min) Good for: Most research needs, balanced depth and speed
deep: Exhaustive research (10+ sources, ~15-20 min) Good for: Complex topics, academic research, thorough analysis
Search Tool Example Response
The search results include rich data:
🔍 Response Types
Knowledge Graph
Contains entity information when available:
Title and type
Website URL
Description
Key attributes
Organic Results
List of search results including:
Title and URL
Snippet (description)
Position in results
Sitelinks when available
People Also Ask
Common questions related to the search:
Question text
Answer snippet
Source link
Related Searches
List of related search queries users often make.
📊 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 detailed information about the metrics collected to improve search quality.
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
Serper API for providing the Google search capabilities
Model Context Protocol for the MCP framework
PostHog for analytics capabilities
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables integration of Google search functionality into MCP-enabled applications using the Serper API, providing rich search results, configurable parameters, and efficient response handling.
- ✨ Features
- 🚀 Installation
- ⚙️ Configuration
- 🔌 Integration
- 🛠 Usage
- 🔍 Response Types
- 📊 Quality Metrics
- 🤝 Contributing
- 📝 License
- 🙏 Acknowledgments
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityAn MCP server implementation that integrates the SearxNG API, providing web search capabilities.Last updated -21,333247MIT License
- -securityFlicense-qualityAn MCP server that integrates with SerpApi to retrieve search results from multiple search engines including Google, Bing, Yahoo, and others, enabling fast access to both live and archived search data.Last updated -16
- AsecurityAlicenseAqualityA powerful MCP server that enables parallel Google searching with multiple keywords simultaneously, providing structured results while handling CAPTCHAs and simulating user browsing patterns.Last updated -1169209MIT License
- -securityFlicense-qualityAn MCP Server that provides access to Google's Search Console API, allowing users to interact with website search performance data and manage search presence through natural language.Last updated -