Provides Google Web Search functionality using the Gemini API. Requires a Google API Key or OAuth credentials.
An MCP (Model Context Protocol) server that provides Google Web Search functionality using the Gemini API. This server is extracted from the official Gemini CLI's web search tool.
npm install -g gemini-google-web-search-mcp
git clone https://github.com/yourusername/gemini-google-web-search-mcp.git
cd gemini-google-web-search-mcp
npm install
npm run build
Visit Google AI Studio to create your API key.
Add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Option 1: API Key Authentication
{
"mcpServers": {
"google-web-search": {
"command": "node",
"args": ["/path/to/gemini-google-web-search-mcp/dist/index.js"],
"env": {
"GOOGLE_API_KEY": "your-api-key-here"
}
}
}
}
Option 2: OAuth Authentication (No API Key Required)
{
"mcpServers": {
"google-web-search": {
"command": "node",
"args": ["/path/to/gemini-google-web-search-mcp/dist/index-codeassist.js"],
"env": {
"USE_OAUTH": "true"
}
}
}
}
Once configured, the google_web_search
tool will be available in Claude Desktop. You can use it by asking Claude to search for information:
GOOGLE_API_KEY
or GEMINI_API_KEY
: Your Google API key (required)GEMINI_MODEL
: Gemini model to use (default: gemini-2.0-flash-exp
)USE_OAUTH
: Set to true
to use OAuth authentication (experimental, not fully supported)GOOGLE_APPLICATION_CREDENTIALS
: Path to service account credentials (optional)The easiest way to authenticate is using an API key:
export GOOGLE_API_KEY=your-api-key-here
OAuth authentication uses Google's Code Assist API, which provides web search functionality with Google login.
Setup Steps:
Set OAuth credentials (if using custom OAuth app):
export OAUTH_CLIENT_ID=your-oauth-client-id
export OAUTH_CLIENT_SECRET=your-oauth-client-secret
Run the automated setup script:
./setup-gcp.sh
Or manually configure:
# Set your Google Cloud project ID
export GOOGLE_CLOUD_PROJECT=your-project-id
# Enable required APIs
gcloud services enable cloudaicompanion.googleapis.com
# Set up authentication
gcloud auth application-default login \
--scopes=https://www.googleapis.com/auth/cloud-platform,https://www.googleapis.com/auth/generative-language.retriever
Use OAuth authentication:
export USE_OAUTH=true
npm run dev:cli -- "your search query"
Requirements:
Note: This uses the same authentication flow as Gemini CLI and accesses Google's Code Assist API for web search functionality.
npm run build
npm run dev
# Set your API key
export GOOGLE_API_KEY=your-api-key-here
# Run the test
npm test
This server implements the Model Context Protocol with:
google_web_search
query
(string) - The search queryApache 2.0 - This project is derived from Google's Gemini CLI which is licensed under Apache 2.0.
This MCP server is based on the web search functionality from Google's official Gemini CLI.
Contributions are welcome! Please feel free to submit a Pull Request.
A full-text search server for Jewish texts and literature.
Search for news articles using the Naver News API. Requires Naver News API credentials.
Kagi search API integration
An MCP server for expert discovery, registration, and context injection, utilizing vector and graph databases.
Search Engine made for AIs by Exa
Search and get up-to-date information about NPM, Cargo, PyPi, and NuGet packages.
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Query Shodan's database of internet-connected devices and vulnerabilities using the Shodan API.
Enhances LLM responses with factual, real-time web content using Jina AI's grounding capabilities.
Web search using the Perplexity API with automatic model selection based on query intent.