Gemini

A Model Context Protocol (MCP) server that enables Claude Desktop to interact with Google's Gemini AI - featuring 7 tools with Smart Tool Intelligence that learns from your usage patterns

javascript

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "garblesnarff-gemini-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/gemini-mcp-server/gemini-server.js"
      ],
      "env": {
        "OUTPUT_DIR": "/path/to/output",
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Gemini MCP Server is a self-learning MCP server that combines seven AI-powered tools with context-aware prompts to adapt to your preferences. It helps you generate images, edit media, chat with an intelligent assistant, transcribe audio, run Python code in a sandbox, analyze videos, and extract details from images—all while learning from your interactions to improve over time.

How to use

You install and run the Gemini MCP Server locally, then connect to it from your MCP client (such as Claude Desktop) to start using its tools. Start by configuring your client with the Gemini server entry, then choose a tool to perform your task. The system enhances prompts based on the current context, learns from successful interactions, and applies improvements in future sessions. When you ask for a task, you’ll see results from media generation, editing, transcription, coding, video insights, or image analysis, with the assistant adapting to your preferences over time.

How to install

Prerequisites: ensure you have Node.js and npm installed, and you have Git available on your machine.

Clone the project repository.
Install dependencies.
Set up your Gemini API key and optional configurations.

Install and run steps

git clone https://github.com/garblesnarff/gemini-mcp-server.git
cd gemini-mcp-server
npm install

Configure your environment and run the server

cp .env.example .env

Add your Gemini API key and optional settings

# Edit the environment file to include your API key and optional settings
GEMINI_API_KEY=your_actual_api_key_here
OUTPUT_DIR=/path/to/your/output/directory  # Optional
DEBUG=false  # Optional

Running the server

npm start
# or for development with debug logging:
npm run dev

Integration with Claude Desktop

{
  "mcpServers": {
    "gemini": {
      "command": "node",
      "args": ["/path/to/gemini-mcp-server/gemini-server.js"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Available tools

generate_image

Create images from text prompts using Gemini 2.0 Flash with optional context to influence style and details.

gemini-edit-image

Edit an existing image by providing a natural language instruction to describe the desired change.

gemini-chat

Engage in interactive, context-aware conversations with the Gemini AI that can adapt to your needs and preferences.

gemini-transcribe-audio

Transcribe audio files to text with optional verbatim mode to capture every utterance and nuance.

gemini-code-execute

Run Python code in a secure sandbox environment and return the output and results.

gemini-analyze-video

Analyze video content to produce summaries, transcripts, and insights.

gemini-analyze-image

Extract objects, text, and detailed descriptions from images with optional analysis scope.

Built by

VeilStrat

AI signals for GTM teams