Web Search MCP Server

Overview

Web Search is a Model Context Protocol (MCP) server that enables AI assistants to perform web searches using Google search results without requiring any API keys or paid services. This tool is perfect for enhancing your AI workflows with real-time information from the web.

Installation

To install and set up the Web Search MCP server:

1. Clone the repository:

   git clone https://github.com/pskill9/web-search.git
   cd web-search
   

2. Install dependencies:

   npm install
   

3. Build the server:

   npm run build
   

4. Configure your MCP client to use the server by adding it to your configuration file.

Configuration

The Web Search MCP server is designed to work with various MCP clients including Claude and other compatible systems. Add the following configuration to your MCP client:

For Claude extensions or other MCP clients, add this to your configuration:

{
  "mcpServers": {
    "web-search": {
      "command": "node",
      "args": ["/path/to/web-search/build/index.js"]
    }
  }
}

Make sure to replace /path/to/web-search with the actual path where you cloned the repository.

Usage

Once configured, you can use the Web Search MCP server to perform web searches directly from your AI assistant. The server provides a simple interface for searching the web and returns structured results.

When making search requests, you can specify:

• The search query (required)
• The number of results to return (optional, default is 5, maximum is 10)

Limitations

Since this tool uses web scraping of Google search results, there are some important limitations to be aware of:

1. Rate Limiting: Google may temporarily block requests if too many searches are performed in a short time. To avoid this:

   • Keep searches to a reasonable frequency
   • Use the limit parameter judiciously
   • Consider implementing delays between searches if needed

2. Result Accuracy:

   • The tool relies on Google's HTML structure, which may change
   • Some results might be missing descriptions or other metadata
   • Complex search operators may not work as expected

3. Legal Considerations:

   • This tool is intended for personal use
   • Respect Google's terms of service
   • Consider implementing appropriate rate limiting for your use case

Troubleshooting

If you encounter issues with the Web Search MCP server:

1. Ensure the server is properly built and running
2. Check that your MCP client configuration is correct
3. Verify that your search queries are properly formatted
4. If searches fail, you may be experiencing rate limiting from Google - wait a while before trying again

For persistent issues, check the GitHub repository for updates or open an issue to report the problem.