Serper MCP Server

What does “Serper” MCP Server do?

The Serper MCP Server is a Model Context Protocol (MCP) server that provides Google Search capabilities via the Serper API. It acts as a bridge between AI assistants and Google’s search infrastructure, enabling LLMs and agents to retrieve real-time search information directly from Google. Through the Serper MCP Server, AI clients can access a wide range of Google search results, including web, images, videos, news, maps, reviews, shopping, and more. This enhances AI development workflows by allowing assistants to answer queries, gather up-to-date facts, extract structured data, and interact with search-driven resources, making it a powerful tool for research, automation, and workflow augmentation.

List of Prompts

No prompt templates are mentioned in the repository or documentation.

List of Resources

No specific MCP resources (readable context objects) are documented or exposed by the Serper MCP Server.

List of Tools

• google_search — Executes a Google web search using customizable parameters.
• google_search_images — Performs a Google Images search with various options.
• google_search_videos — Retrieves video results from Google search.
• google_search_places — Searches for places using Google’s location data.
• google_search_maps — Provides map-related search results from Google.
• google_search_reviews — Gathers Google reviews for businesses or locations.
• google_search_news — Fetches recent news results from Google.
• google_search_shopping — Returns shopping/product listings from Google Shopping.
• google_search_lens — Interfaces with Google Lens for visual search.
• google_search_scholar — Queries Google Scholar for academic content.
• google_search_parents — Specialized search (context not detailed).
• google_search_autocomplete — Fetches Google’s autocomplete suggestions.
• webpage_scrape — Scrapes content from a specified webpage.

Use Cases of this MCP Server

• Real-Time Information Retrieval: Enables AI agents to answer user queries with up-to-date facts and news by leveraging Google search results.
• Media Content Discovery: Supports searching for images, videos, and maps, allowing developers to build multimedia-rich applications.
• Business Intelligence and Reviews: Facilitates collection of reviews, places, and business data for market analysis and customer feedback aggregation.
• Academic Research: Provides access to scholarly articles and research papers via Google Scholar search.
• Web Content Extraction: Scrapes webpage content, supporting workflows like summarization, data extraction, and knowledge base augmentation.

How to set it up

Windsurf

1. Ensure you have Node.js installed.
2. Locate your Windsurf configuration file.
3. Add the Serper MCP Server to the mcpServers object:

   {
     "mcpServers": {
       "serper": {
         "command": "uvx",
         "args": ["serper-mcp-server"],
         "env": {
           "SERPER_API_KEY": "<Your Serper API key>"
         }
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the MCP server is running and accessible.

Claude

1. Install uv on your system.
2. In claude_desktop_config.json, add the Serper MCP Server:

   {
     "mcpServers": {
       "serper": {
         "command": "uvx",
         "args": ["serper-mcp-server"],
         "env": {
           "SERPER_API_KEY": "<Your Serper API key>"
         }
       }
     }
   }
   

3. Save the file and restart Claude Desktop.
4. Confirm the server loads in the Claude interface.

Cursor

1. Make sure Python and uv are installed.
2. In Cursor’s MCP server configuration, add:

   {
     "mcpServers": {
       "serper": {
         "command": "uvx",
         "args": ["serper-mcp-server"],
         "env": {
           "SERPER_API_KEY": "<Your Serper API key>"
         }
       }
     }
   }
   

3. Save changes and restart Cursor.
4. Test by running a search via Cursor’s command palette.

Cline

1. Install serper-mcp-server via pip or add to requirements.txt:

   serper-mcp-server
   

2. In your Cline configuration, add:

   {
     "mcpServers": {
       "serper": {
         "command": "uvx",
         "args": ["serper-mcp-server"],
         "env": {
           "SERPER_API_KEY": "<Your Serper API key>"
         }
       }
     }
   }
   

3. Save and restart Cline.
4. Confirm successful connection to the MCP server.

Securing API Keys

Store sensitive API keys using environment variables in your configuration. Example:

{
  "mcpServers": {
    "serper": {
      "command": "uvx",
      "args": ["serper-mcp-server"],
      "env": {
        "SERPER_API_KEY": "<Your Serper API key>"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "serper": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “serper” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

Serper MCP Server is focused and practical, offering a rich set of Google-powered search tools for AI agents. However, it lacks explicit prompt templates, resource definitions, and sampling/root support. Its documentation is concise but functional. Overall, it’s a solid utility for search augmentation but not a full-featured MCP server.

MCP Score