Gemini Web & Image Automation connects Claude to Google Gemini's web interface via an integrated Model Context Protocol (MCP) server daemon. It automates end-to-end AI image generation with full-resolution extraction, session handling, model switching (Pro, Quick, Think), and reference image uploading without requiring manual browser navigation or API keys. Designed for autonomous agents and local development environments, it ensures reliable, step-by-step UI automation with built-in progress tracking and diagnostics.
주요 기능
01Enables generating public share links and extracting base64 image data
02Provides built-in browser daemon management and diagnostic probing via MCP
03Automates end-to-end Gemini image generation and local full-resolution file downloads
04Controls chat sessions, model switching (Pro, Quick, Think), and temporary chats
05Supports reference image uploading and multi-modal image-to-image workflows
06829 GitHub stars
사용 사례
01Iterating on visual concepts by uploading reference images and text prompts to Gemini
02Automating web-based Gemini interactions without needing paid API credentials
03Generating high-resolution AI illustrations and posters directly from agent workflows