mcpField
G
Google Search MCP Server

Google Search MCP Server

Local
github.com/gradusnikovSearch6Updated 86w ago
Repository

About Google Search MCP Server

Google Search MCP Server is an MCP server for Google Custom Search, intended for MCP clients that need web search results. It uses a Google API key and Custom Search Engine ID for configuration.

Key features

  1. 01Google Custom Search access
  2. 02API key and CSE ID configuration
  3. 03Claude Desktop setup via Smithery

Use cases

  1. 01Search the web from an MCP client
  2. 02Connect Google Custom Search to Claude Desktop

MCP support

Exposes Google Custom Search functionality to MCP clients as an MCP server.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Google Search MCP Server

smithery badge

A Model Context Protocol (MCP) server that provides Google Custom Search functionality.

Installation

Installing via Smithery

To install google-search-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gradusnikov/google-search-mcp-server --client claude
Manual Installation
  1. Clone the repository:
git clone https://github.com/gradusnikov/google-search-mpc-server.git
cd google-search-mpc-server
  1. Install dependencies:
pip install fastmcp google-api-python-client python-dotenv

Configuration

Create a .env file in the project root with the following variables:

GOOGLE_API_KEY=your_google_api_key
GOOGLE_CSE_ID=your_custom_search_engine_id

To obtain these credentials:

  1. Create a Google Cloud project and enable the Custom Search API
  2. Generate an API key from the Google Cloud Console
  3. Create a Custom Search Engine at https://cse.google.com/cse/all and get its ID

Usage

Start the server using MCP:

mcp run google_search_mcp_server.py

or add the server to Claude Desktop app CLAUDE_DIRECTORY/claude_desktop_config.json. For example if you are using Windows Subsystem for Linux (WSL) it may look like this:

"google-search": {
            "command": "wsl.exe",
            "args": [
                "bash",
                "-c",
                "source /home/[user]/anaconda3/etc/profile.d/conda.sh && conda activate mcp && /home/[user]/anaconda3/bin/mcp run /home/[user]/google-search-mpc-server/google_search_mcp_server.py"
            ]
        },

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.