Gemini Vision is an AI-powered media analysis tool that uses Google's Gemini models to extract insights from images and videos. It provides fast visual understanding capabilities through a simple API interface. Key features of Gemini Vision: - Analyze images from URLs with automatic MIME type detection and a 16 MB size limit per image - Process YouTube videos directly via streaming without any file size restrictions - Scene summarization, object identification, and key detail extraction for reports - Configurable model selection with default to `gemini-flash-lite-latest` - Batch analysis of multiple images in a single tool call - Support for Google AI Studio API keys via environment variables

image-mcp-server-gemini

[](https://smithery.ai/server/@Artin0123/gemini-image-mcp-server)

> This is remote server, use local version for local images and videos.

Features

Installation

Installing via Smithery

Install the server in Claude Desktop:

npx -y @smithery/cli install @Artin0123/gemini-image-mcp-server --client claude

Manual Installation

# Clone the repository
git clone https://github.com/Artin0123/gemini-vision-mcp.git
cd gemini-vision-mcp
Install dependencies
npm install
Compile TypeScript to dist/
npm run build

Configuration

Create a Gemini API key in Google AI Studio and provide GEMINI_API_KEY to the server.

{
  "mcpServers": {
    "gemini-media": {
      "command": "node",
      "args": ["/absolute/path/to/gemini-vision-mcp/dist/index.js"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here",
        "GEMINI_MODEL": "models/gemini-flash-lite-latest"
      }
    }
  }
}

If no key is supplied, the server can still start (handy for automated scans), but any tool invocation will return a configuration error until a valid API key is configured.

Model override

The server defaults to models/gemini-flash-lite-latest. Override it by either:

> Setting the GEMINI_MODEL environment variable, or Providing modelName in the Smithery/SDK configuration schema.

Available tools

Image URLs are downloaded and processed with a 16 MB size limit to ensure fast response times. Files exceeding this limit will result in an error message indicating the actual file size.

YouTube videos are streamed directly by Gemini API without downloading, so there is no size restriction.

Prompt examples

Please analyze this product photo: https://teimg-bgr.pages.dev/file/mvYT6KeF.webp

Extract the main talking points from this clip: https://www.youtube.com/watch?v=dQw4w9WgXcQ

Development

npm install
npm test
npm run build

The test suite exercises URL forwarding, MIME handling, and configuration fallbacks.

License

MIT