AI Vision
Provides AI-powered image and video analysis capabilities through a Model Context Protocol server, leveraging Google Gemini and Vertex AI models.
소개
The AI Vision MCP server empowers developers and applications with advanced visual intelligence. It integrates seamlessly with Model Context Protocol clients, offering robust capabilities to analyze both images and videos. By supporting powerful Google Gemini and Vertex AI models, it enables multimodal analysis, flexible file handling from various sources (URLs, local files, base64), and secure storage integration with Google Cloud Storage. The server is built with TypeScript, ensuring strict type checking, and features comprehensive Zod-based validation and resilient error handling with retries and circuit breakers.
주요 기능
- Dual AI Provider Support (Google Gemini and Vertex AI)
- Multimodal Analysis (Image and Video Content)
- Flexible File Handling (URLs, Local Files, Base64)
- Google Cloud Storage Integration for Vertex AI
- Robust Error Handling with Retries and Circuit Breakers
- 7 GitHub stars
사용 사례
- Perform detailed video content analysis from YouTube URLs or local files.
- Integrate advanced image analysis into AI assistants and tools via MCP clients.
- Compare multiple images to identify differences, similarities, or specific qualities for various applications.
