Gemini Search

Provides Gemini 2.0 powered search that combines Gemini API with Google Search to deliver up-to-date answers.

javascript

24

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lorhlona-geminiserchmcp": {
      "command": "node",
      "args": [
        "path/to/gemini-search-server/build/index.js"
      ],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Gemini Search MCP Server powers up-to-date responses by leveraging the Gemini API together with Google Search. This server is designed to be used in conjunction with an AI assistant, enabling Gemini-based search functionality once loaded into the assistant environment.

How to use

Load the Gemini Search MCP Server into your MCP client or assistant. You will interact with it as a standard MCP server that supports the search tool. When you issue a query through the MCP client, the server uses Gemini 2.0 and Google Search to generate an answer and return relevant results. Use it to fetch current information and provide well-sourced responses within your conversational flow.

How to install

Prerequisites: Node.js installed on your system.

Step 1: Install dependencies.

npm install

Step 2: Build the server.

npm run build

Step 3: Set up your Gemini API key. Create a file named .env in the project root and add the following content.

GEMINI_API_KEY=your_api_key_here

Note: You obtain your Gemini API key from Google AI Studio.

Configuration and startup guidance

To run the MCP server locally for testing with an MCP client, use the following runtime command and environment variable.

node path/to/gemini-search-server/build/index.js

Environment:

GEMINI_API_KEY=your_api_key_here

Additional notes

Debugging MCP servers is facilitated by MCP Inspector, since servers communicate via stdio. To start the inspector, run the development helper.

npm run inspector

Available tools

search

Generates answers using Gemini 2.0 and Google Search. Accepts a query, returns Gemini's response and relevant search results.