G Search MCP

🚀 G-Search MCP

A powerful MCP server for Google search, supporting parallel searches with multiple keywords simultaneously.

This project is modified based on google-search.

✨ Features

• Parallel Search: Supports searching on Google with multiple keywords simultaneously, enhancing search efficiency.
• Browser Optimization: Opens multiple tabs in a single browser instance for efficient parallel searches.
• Automatic Verification Handling: Intelligently detects CAPTCHA and enables the visible browser mode for user verification when necessary.
• User Behavior Simulation: Mimics real user browsing habits to reduce the risk of being detected by search engines.
• Structured Data Return: Returns structured search results in JSON format for easy subsequent processing and analysis.
• Configurable Parameters: Supports various parameter configurations, such as search result limits, timeout settings, and region settings.

🚀 Quick Start

Run directly using npx:

npx -y g-search-mcp

When installing for the first time, execute the following command in the terminal to install the required browser:

npx playwright install chromium

Debug Mode

Use the --debug option to run in debug mode (show the browser window):

npx -y g-search-mcp --debug

📦 Configuration of MCP

Configure this MCP server in Claude Desktop: MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "g-search": {
      "command": "npx",
      "args": ["-y", "g-search-mcp"]
    }
  }
}

💻 Usage Examples

Basic Usage

Execute parallel searches:

g-search-mcp search --queries keyword1,keyword2 --limit 5

Fetch real-time exchange rate data:

g-search-mcp fetcher --url https://www.google.com/finance/markets/currencies/EURUSD=X --xpath //*[@class=' financial-data-bucket__value']

Returned Results

Search results will be returned in JSON format. Here is an example:

{
  "results": [
    {
      "title": "Content related to keyword 1",
      "url": "https://example.com/keyword1",
      "snippet": "Brief description of keyword 1..."
    },
    {
      "title": "Content related to keyword 2",
      "url": "https://example.com/keyword2",
      "snippet": "Brief description of keyword 2..."
    }
  ]
}

Usage Tips

• Handling Special Website Scenarios: Extract and process content from specific web pages through custom scripts.
• Debugging and Troubleshooting:
  • Check if the browser driver is correctly installed and up-to-date.
  • Ensure a stable network connection to avoid search failures due to timeouts.
  • Regularly clear the cache to improve search efficiency.

📦 Installation

1. Clone the repository:

git clone https://github.com/jae-jae/g-search-mcp.git
cd g-search-mcp

2. Install dependencies:

npm install

3. Install the Playwright browser:

npm run install-browser

4. Build the server:

npm run build

🔧 Technical Details

Automatic Rebuilding (Development Mode)

npm run watch

Debugging with MCP Inspector

npm run inspector

📚 Related Projects

• fetcher-mcp: A powerful MCP server for scraping web page content using the Playwright headless browser. Features include intelligent content extraction, parallel processing, resource optimization, etc., making it an ideal choice for web crawlers.

📄 License

This project is licensed under the MIT License.