Happy slice of mcp pizzaMCP.pizza

mcp-server-gemini

MCP.Pizza Chef: aliargun

Six things become possible once it is set up: your assistant can put a question to Gemini and read the answer back, describe an image, measure how long a piece of text is, list the models it knows about, prepare text for similarity matching, and explain its own settings. You supply a free key from Google AI Studio and paste it into your assistant's configuration. Worth knowing: the model list is written into the code and stops at the Gemini 2.5 family, with no changes since July 2025.

Unmaintained · no code changes since July 2025; model list stops at Gemini 2.5
Images/Design
Web/Research
Writing

Use This MCP server To

Ask Gemini a question without leaving the assistant I already use Get a second opinion from a different AI on the same question Have Gemini describe a screenshot or photo I paste in Ask a question that needs a fresh web search behind it Check how long a document is before I send it anywhere Keep a back-and-forth going with Gemini across several questions

README

Gemini MCP Server

smithery badge npm version License: MIT TypeScript MCP Version

A powerful MCP (Model Context Protocol) server that brings Google's latest Gemini AI models to your favorite development environment. Access Gemini 2.5's thinking capabilities, vision analysis, embeddings, and more through a seamless integration.

🚀 Works with: Claude Desktop, Cursor, Windsurf, and any MCP-compatible client
🎯 Why use this: Get Gemini's cutting-edge AI features directly in your IDE with full parameter control
📚 Self-documenting: Built-in help system means you never need to leave your editor

Features

  • 6 Powerful Tools: Text generation, image analysis, token counting, model listing, embeddings, and self-documenting help
  • Latest Gemini Models: Support for Gemini 2.5 series with thinking capabilities
  • Advanced Features: JSON mode, Google Search grounding, system instructions, conversation memory
  • Full MCP Protocol: Standard stdio communication for seamless integration with any MCP client
  • Self-Documenting: Built-in help system - no external docs needed
  • TypeScript & ESM: Modern, type-safe implementation

Supported Models

Model Context Features Best For
gemini-2.5-pro 2M tokens Thinking, JSON, Grounding Complex reasoning
gemini-2.5-flash ⭐ 1M tokens Thinking, JSON, Grounding General use
gemini-2.5-flash-lite 1M tokens Thinking, JSON Fast responses
gemini-2.0-flash 1M tokens JSON, Grounding Standard tasks
gemini-1.5-pro 2M tokens JSON Legacy support

Quick Start

mcp-server-gemini FAQ

Is this still being maintained?
It has had no code changes since July 2025, over a year ago. It still installs and runs, but the list of Gemini models is baked into the code and ends at the 2.5 family, so anything Google released since then will not appear.
Do I need a key, and does it cost money?
Yes to the key — you create one free at Google AI Studio and paste it into your settings. Light use is typically free, but Google, not this project, decides what heavy use costs.
Which apps does it work in?
Claude Desktop, Cursor and Windsurf are documented, and any other app that supports MCP should work. Each one takes the same short block of settings text.
Can I use this to have Gemini look at an image for me?
Yes. There is a dedicated image tool that will describe a picture or pull the text out of it, though it is limited to the handful of model names hard-coded in the project.
Can it look things up on the live web?
Yes, if you ask for it. There is an option that lets Gemini search Google before answering, and it works on the newer models in its list. It is off unless requested.
How hard is it to set up?
Easy end of the middle. Get a key, paste roughly six lines into your assistant's settings file, restart the app. No coding, though you do edit a settings file by hand.