Overview

The Web Search MCP Server allows you to perform Google searches directly from your AI workflows without requiring any API keys. This server scrapes Google search results and returns them in a structured format that's easy to process.

Installation

To install the Web Search MCP Server:

1. Clone the repository:

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

2. Install the dependencies:

npm install

3. Build the server:

npm run build

4. Configure the MCP server in your environment:

For VSCode (Claude Dev Extension):

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

For Claude Desktop:

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

Available Tools

search

The search tool allows you to perform web searches using Google.

Parameters:

• query (string, required): The search query to execute
• limit (number, optional): Number of results to return (default: 5, max: 10)

Returns: An array of search results, each containing:

• title: The title of the search result
• url: The URL of the search result
• description: A brief description of the search result

Example Usage:

use_mcp_tool({
  server_name: "web-search",
  tool_name: "search",
  arguments: {
    query: "latest AI developments",
    limit: 3
  }
})

Example Response:

[
  {
    "title": "Recent Advances in Artificial Intelligence - Example Site",
    "url": "https://example.com/ai-developments",
    "description": "A comprehensive overview of the latest developments in artificial intelligence research and applications..."
  },
  {
    "title": "AI News and Updates - Another Example",
    "url": "https://another-example.com/ai-news",
    "description": "Stay updated with the most recent breakthroughs in AI technology..."
  },
  {
    "title": "The Future of AI - Third Example",
    "url": "https://third-example.com/future-ai",
    "description": "Exploring the potential future directions of artificial intelligence..."
  }
]

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

Best Practices

• Use specific, targeted search queries for better results
• Implement error handling in your code to manage potential rate limiting
• Consider caching frequently requested search results to reduce the number of requests
• Use the limit parameter to request only the number of results you actually need