mcp-google-search MCP Server

What does “mcp-google-search” MCP Server do?

The mcp-google-search MCP Server is a Model Context Protocol server that enables AI assistants to perform web searches using the Google Custom Search API and extract content from webpages. By acting as a bridge between AI clients and the vast resources of the web, it allows large language models (LLMs) to access up-to-date information, perform research, and enhance their knowledge with real-time data. The server exposes tools for both searching the web and reading webpage contents, making it useful for a variety of development and agentic workflows that require reliable access to external online data.

List of Prompts

No explicit prompt templates are mentioned in the available documentation.

List of Resources

No explicit resources are documented in the available files or README.

List of Tools

• search
  Performs a web search using the Google Custom Search API. Allows specification of the search query and the number of results (up to 10). Returns structured results including titles, links, and snippets for each result.

• read_webpage
  Extracts and parses the content of a provided webpage URL. Fetches the page, removes scripts and styles, and returns the cleaned title, main text, and URL for context-aware processing.

Use Cases of this MCP Server

• Real-Time Web Research
  Developers and AI agents can access the latest information from the web, enabling up-to-date answers and research for knowledge-intensive tasks.

• Fact-Checking and Verification
  By searching across trusted websites and fetching page content, this server can help verify facts, claims, or sources in real time.

• Content Summarization
  AI assistants can fetch and read articles or pages, then summarize their content for users or downstream workflows.

• Automated Knowledge Gathering
  Enables building agents that autonomously gather information from multiple web sources and compile structured reports or datasets.

• Learning and Exploration
  Assists in codebase exploration or technical learning by searching for documentation, tutorials, or relevant discussions across the web.

How to set it up

Windsurf

1. Prerequisites: Ensure Node.js and npm are installed.
2. Locate Configuration: Find your Windsurf configuration file (typically windsurf_config.json).
3. Add MCP Server: Insert the following snippet into the mcpServers object:

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

4. Save & Restart: Save the configuration and restart Windsurf.
5. Verify: Check that the server is running and available as a tool.

Claude

1. Prerequisites: Install Node.js and npm.
2. Install via Smithery:
   Run:

   npx -y @smithery/cli install @adenot/mcp-google-search --client claude
   

3. Edit Configuration:
   On Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
   On Windows: %APPDATA%/Claude/claude_desktop_config.json
4. Insert JSON:

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

5. Save & Restart: Save changes and restart Claude Desktop.
6. Verify: Ensure the MCP server appears in your tools.

Cursor

1. Prerequisites: Node.js and npm installed.
2. Configuration File: Open your Cursor config (e.g., cursor_config.json).
3. Add MCP Server:

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

4. Save & Restart: Save config and restart Cursor.
5. Verify: Check server availability.

Cline

1. Prerequisites: Node.js and npm.
2. Locate Config: Find your Cline configuration file.
3. Update MCP Servers:

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

4. Save & Restart: Save the file and restart Cline.
5. Verify Setup: Confirm the MCP server is loaded.

Note:
Always secure your API keys using environment variables as shown in the "env" block of the JSON examples. Do not commit API keys to version control.

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:

{
  "google-search": {
    "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 “google-search” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the two tables above, mcp-google-search MCP Server provides the core tool functionality well and is easy to set up, but lacks documentation on prompts, resources, roots, and sampling support. It would rate around a 6/10 for overall completeness and developer experience.

MCP Score