MCP Gemini Google Search MCP Server

MCP server for Google Search using Gemini

Local serverstdioTypeScript

What is the MCP Gemini Google Search MCP server?

MCP server for Google Search using Gemini. That is what the mcp gemini google search mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This project is inspired by the GoogleSearch tool from gemini-cli.

  • Uses Gemini's built-in Grounding with Google Search feature
  • Provides real-time web search results with source citations
  • Compliant with MCP standard protocol
  • Supports stdio transport
  • Supports both Google AI Studio and Vertex AI

The tools it exposes

The server publishes 1 tool. What each one is for:

  • google_search — In summary, TypeScript is continuously evolving with new features and improvements aimed at enhancing developer productivity, code quality, and

What it needs from you

Configuration is passed through the environment: GEMINI_API_KEY, GEMINI_MODEL, GEMINI_PROVIDER, VERTEX_PROJECT_ID, VERTEX_LOCATION. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Node.js 18 or later - Google AI Studio API key (Get one here) or Google Cloud Project with Vertex AI enabled

Getting it running

mcp-gemini-google-search on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Gemini Google Search's toolset — google_search — is a fair guide to whether it matches your workflow. It is maintained by yukukotani; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
google_searchIn summary, TypeScript is continuously evolving with new features and improvements aimed at enhancing developer productivity, code quality, and performance.[6]

How to install the MCP Gemini Google Search MCP server

{
  "mcpServers": {
    "gemini-google-search": {
      "command": "npx",
      "args": ["-y", "mcp-gemini-google-search"],
      "env": {
        "GEMINI_API_KEY": "your-value",
        "GEMINI_MODEL": "your-value",
        "GEMINI_PROVIDER": "your-value",
        "VERTEX_PROJECT_ID": "your-value",
        "VERTEX_LOCATION": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js 18 or later - Google AI Studio API key (Get one here) or Google Cloud Project with Vertex AI enabled
VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes
GEMINI_MODELConfiguration value read at startup.Optional
GEMINI_PROVIDERConfiguration value read at startup.Optional
VERTEX_PROJECT_IDConfiguration value read at startup.Optional
VERTEX_LOCATIONConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Gemini Google Search to google search.

Frequently asked questions

It connects MCP Gemini Google Search to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (google_search) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Gemini Google Search directly.