A powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.

This project is modified from google-search.

• Parallel Searching: Supports searching with multiple keywords on Google simultaneously, improving search efficiency
• Browser Optimization: Opens multiple tabs in a single browser instance for efficient parallel searching
• Automatic Verification Handling: Intelligently detects CAPTCHA and enables visible browser mode for user verification when needed
• User Behavior Simulation: Simulates real user browsing patterns to reduce the possibility of detection by search engines
• Structured Data: Returns structured search results in JSON format for easy processing and analysis
• Configurable Parameters: Supports various parameter configurations such as search result limits, timeout settings, locale settings, etc.

Run directly with npx:

npx -y g-search-mcp

First time setup - install the required browser by running the following command in your terminal:

npx playwright install chromium

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

npx -y g-search-mcp --debug

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"]
    }
  }
}

• search - Execute Google searches with multiple keywords and return results
  • Uses Playwright browser to perform searches
  • Supports the following parameters:
    • queries: Array of search queries to execute (required parameter)
    • limit: Maximum number of results to return per query, default is 10
    • timeout: Page loading timeout in milliseconds, default is 60000 (60 seconds)
    • noSaveState: Whether to avoid saving browser state, default is false
    • locale: Locale setting for search results, default is en-US
    • debug: Whether to enable debug mode (showing browser window), overrides the --debug flag in command line

Example usage:

Use the search tool to search for "machine learning" and "artificial intelligence" on Google

Example response:

{
  "searches": [
    {
      "query": "machine learning",
      "results": [
        {
          "title": "What is Machine Learning? | IBM",
          "link": "https://www.ibm.com/topics/machine-learning",
          "snippet": "Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy."
        },
        ...
      ]
    },
    {
      "query": "artificial intelligence",
      "results": [
        {
          "title": "What is Artificial Intelligence (AI)? | IBM",
          "link": "https://www.ibm.com/topics/artificial-intelligence",
          "snippet": "Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities of the human mind."
        },
        ...
      ]
    }
  ]
}

• Search Result Quantity: For more search results:

  Please return the top 20 search results for each keyword
  

  This will set the limit: 20 parameter.

• Increase Timeout Duration: For slow loading situations:

  Please set the page loading timeout to 120 seconds
  

  This will adjust the timeout parameter to 120000 milliseconds.

• Change Search Region: Specify a different locale setting:

  Please use Chinese locale (zh-CN) for searching
  

  This will set the locale: "zh-CN" parameter.

• Dynamic Debug Activation: To display the browser window during a specific search operation:

  Please enable debug mode for this search operation
  

  This sets debug: true even if the server was started without the --debug flag.

• Node.js 18 or higher
• NPM or Yarn

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 Playwright browser:

npm run install-browser

4. Build the server:

npm run build

npm run watch

npm run inspector

• fetcher-mcp: A powerful MCP server for fetching web page content using Playwright headless browser. Features intelligent content extraction, parallel processing, resource optimization, and more, making it an ideal tool for web content scraping.

Licensed under the MIT License