MCP Catalogs
Home

mcp-gemini-google-search

by yukukotani·79·Score 43

MCP server providing Google Search functionality using Gemini's built-in Grounding with Google Search feature.

ai-llmsearchdeveloper-tools
6
Forks
1
Open issues
10 mo ago
Last commit
2d ago
Indexed

Overview

This MCP server integrates Google Search functionality through Gemini's Grounding with Google Search feature. It provides real-time web search results with proper source citations, making it valuable for information retrieval tasks. The server supports both Google AI Studio and Vertex AI, offering flexibility for different deployment scenarios.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Real-time information retrieval in AI assistants
you:Adding web search capabilities to MCP-compatible clients
you:Research tasks requiring current web data with source verification
you:What API do I need to use this MCP server?
you:Which models are supported?

When to choose this

Choose this when you need Google search capabilities within MCP-compliant AI applications, especially if you're already using Google AI or Vertex AI.

When NOT to choose this

Don't choose this if you need search capabilities from other search engines (like Bing or DuckDuckGo) or if you have concerns about vendor lock-in with Google services.

Tools this server exposes

1 tool extracted from the README
  • google_searchquery: string

    Search Google for information

Comparable tools

mcp-scraperweb-search-mcpbrowser-mcp

Installation

Installation

npm install -g mcp-gemini-google-search

Environment Variables

# For Google AI Studio (default)
export GEMINI_API_KEY="your-api-key-here"
export GEMINI_MODEL="gemini-2.5-flash"  # Optional

# For Vertex AI
export GEMINI_PROVIDER="vertex"
export VERTEX_PROJECT_ID="your-gcp-project-id"
export VERTEX_LOCATION="us-central1"  # Optional

Claude Code Configuration

claude mcp add gemini-google-search \
  -s user \
  -e GEMINI_API_KEY="your-api-key-here" \
  -- npx mcp-gemini-google-search

FAQ

What API do I need to use this MCP server?
You need either a Google AI Studio API key or a Google Cloud Project with Vertex AI enabled.
Which models are supported?
The server defaults to gemini-2.5-flash but supports other Gemini models that support Grounding with Google Search.

Compare mcp-gemini-google-search with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.