Google Web Search (Gemini)

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.

- Google Web Search via Gemini API
- Citation support with source links
- Grounding metadata for accurate information retrieval
- Fully compatible with Claude Desktop and other MCP clients

- Node.js 18+
- Google API Key (Gemini API access)

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

VisitGoogle AI Studioto create your API key.

{ "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, thegoogle_web_searchtool will be available in Claude Desktop. You can use it by asking Claude to search for information:

- "Search for the latest news about MCP protocol"
- "Find information about TypeScript 5.0 features"
- "Look up recent developments in AI safety"

- GOOGLE_API_KEYorGEMINI_API_KEY: Your Google API key (required)
- GEMINI_MODEL: Gemini model to use (default:gemini-2.0-flash-exp)
- USE_OAUTH: Set totrueto 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:

2. OAuth Authentication with Code Assist API (Setup Required)

OAuth authentication uses Google's Code Assist API, which provides web search functionality with Google login.
-

Set OAuth credentials (if using custom OAuth app):

export OAUTH_CLIENT_ID=your-oauth-client-id export OAUTH_CLIENT_SECRET=your-oauth-client-secret

# 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

export USE_OAUTH=true npm run dev:cli -- "your search query"

- Google Cloud project with billing enabled
- Cloud AI Companion API enabled
- Gemini Code Assist subscription (free tier available)

Note: This uses the same authentication flow as Gemini CLI and accesses Google's Code Assist API for web search functionality.

# 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:

- Tool:google_web_search

- Input:query(string) - The search query
- Output: Search results with citations and source links

Apache 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 fromGoogle's official Gemini CLI.

Task/project MCP server with OAuth for Claude, Cursor bridge, semantic search, staged write approval