Google AI Studio

Integrates with Google AI Studio/Gemini API to process multimodal content including images, videos, audio, PDFs, and text files for content generation, analysis, and document conversion tasks.

This MCP server provides Google AI Studio/Gemini API integration with comprehensive file processing capabilities, supporting images, videos, audio, PDFs, and text files for content generation and analysis. Built by eternnoir using TypeScript with the Google GenAI SDK, it offers a single generate_content tool that handles multimodal inputs with configurable parameters for model selection, system prompts, and file limits (up to 10 files per request, 50MB total). The implementation features automatic MIME type detection, base64 file encoding, robust error handling with individual file failure reporting, and support for common use cases like PDF-to-Markdown conversion, image analysis, and audio transcription, making it valuable for document processing workflows, multimodal content analysis, and building AI assistants that need to work with diverse file types through Gemini's advanced capabilities.