关于
Empower AI assistants to visually explore Wikimedia Commons, retrieving a structured list of image metadata alongside a composite image of search result thumbnails. This server acts as 'eyes' for AI models, allowing them to make informed decisions by comparing visual content and detailed information (license, author, dimensions) rather than relying solely on text descriptions. It's designed to help AI agents efficiently find, verify, and select the most relevant images for various creative and informational tasks.