MCP.so
Sign In

Overview

What is Gemini MCP Server?

It implements a Model Context Protocol (MCP) server for Google Search, enabling integration with AI assistants and other MCP-compatible clients.

How to use Gemini MCP Server?

Install dependencies with npm install, set up your Google Custom Search API key in a .env file as GEMINI_API_KEY, then run a test search via npx ts-node src/test.ts or integrate it as an MCP server in your client configuration (e.g., claude_desktop_config.json).

Key features of Gemini MCP Server

  • Provides a googleSearchContent tool for web search results (title, link, snippet).
  • Provides a googleSearchImages tool for image search (Markdown image link).
  • Built on Node.js 18+ with npm package management.
  • Works with any MCP-compatible client.
  • Simple .env‑based credential management.

Use cases of Gemini MCP Server

  • AI assistants retrieving real‑time web search results.
  • Fetching image links for visual content in conversations.
  • Integrating Google Search capabilities into custom MCP pipelines.
  • Testing and prototyping MCP server configurations.

FAQ from Gemini MCP Server

What are the prerequisites?

Node.js 18 or newer and npm are required.

How do I get the required API key?

Obtain a Google Custom Search API key from the Google Custom Search JSON API documentation and place it in a .env file as GEMINI_API_KEY.

What tools does the server provide?

Two tools: googleSearchContent (web search returning titles, links, and snippets) and googleSearchImages (image search returning a Markdown image link for the first result).

How can I integrate this server with Claude or another MCP client?

Add an entry to your MCP settings file (e.g., claude_desktop_config.json) with the command npx ts-node src/index.ts and the GEMINI_API_KEY environment variable set to your key.

What should I do if search fails?

Verify that your API key is correctly set in the .env file or environment, all dependencies are installed (npm install), Node.js 18+ is used, and the server has been restarted after any code changes.

Tags

More from AI & Agents