{
  "markdown": "# image-mcp-server-gemini\n\n[![smithery badge](https://smithery.ai/badge/@Artin0123/gemini-image-mcp-server)](https://smithery.ai/server/@Artin0123/gemini-image-mcp-server)\n\n> This is remote server, use [local version](https://github.com/Artin0123/gemini-vision-mcp/tree/local) for local images and videos.\n\n## Features\n\n- Analyze one or more image URLs with a single tool call.\n- Analyze YouTube videos without downloading files locally.\n- Supply an API key and optionally override the Gemini model via environment variables.\n- **File size limit**: Images are limited to 16 MB to ensure fast processing.\n- **YouTube videos**: No size limit as they are streamed directly by Gemini API.\n\n## Installation\n\n### Installing via Smithery\n\nInstall the server in Claude Desktop:\n\n```bash\nnpx -y @smithery/cli install @Artin0123/gemini-image-mcp-server --client claude\n```\n\n### Manual Installation\n\n```bash\n# Clone the repository\ngit clone https://github.com/Artin0123/gemini-vision-mcp.git\ncd gemini-vision-mcp\n\n# Install dependencies\nnpm install\n\n# Compile TypeScript to dist/\nnpm run build\n```\n\n## Configuration\n\nCreate a Gemini API key in [Google AI Studio](https://aistudio.google.com/app/apikey) and provide `GEMINI_API_KEY` to the server.\n\n```json\n{\n  \"mcpServers\": {\n    \"gemini-media\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/gemini-vision-mcp/dist/index.js\"],\n      \"env\": {\n        \"GEMINI_API_KEY\": \"your_api_key_here\",\n        \"GEMINI_MODEL\": \"models/gemini-flash-lite-latest\"\n      }\n    }\n  }\n}\n```\n\nIf 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.\n\n### Model override\n\nThe server defaults to `models/gemini-flash-lite-latest`. Override it by either:\n\n> Setting the `GEMINI_MODEL` environment variable, or Providing `modelName` in the Smithery/SDK configuration schema.\n\n## Available tools\n\n- `analyze_image`: Analyze one or more image URLs. **Maximum file size: 16 MB per image.**\n- `analyze_youtube_video`: Analyze a YouTube video from URL. No size limit.\n\nImage 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.\n\nYouTube videos are streamed directly by Gemini API without downloading, so there is no size restriction.\n\n### Prompt examples\n\n```\nPlease analyze this product photo: https://teimg-bgr.pages.dev/file/mvYT6KeF.webp\n```\n\n```\nExtract the main talking points from this clip: https://www.youtube.com/watch?v=dQw4w9WgXcQ\n```\n\n## Development\n\n```bash\nnpm install\nnpm test\nnpm run build\n```\n\nThe test suite exercises URL forwarding, MIME handling, and configuration fallbacks.\n\n## License\n\nMIT\n",
  "bytes": 2783,
  "sha": "a15286ea1e699c61d69cd9f9d3336e80a430c3636100be772d37491747b66145",
  "repo_slug": "artin0123/gemini-vision-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_smithery_artin0123_gemini_image_mcp_s_3c52dbbc/readme"
}