Gemini WebAPI

概要

This tool acts as an MCP server, providing a convenient and free gateway to Google Gemini's powerful AI features. It enables users to generate and edit images, engage in text chats, and analyze various file types (like videos, images, PDFs) and URLs, all by leveraging existing browser cookies, thus eliminating the need for traditional API keys. It also offers advanced features such as automatic 2x image upscaling and local watermark removal.

主な機能

• 6 GitHub stars
• Analyzes diverse media including video, images, PDFs, documents, and URLs.
• Removes Gemini's sparkle watermark from generated images using the LaMa neural network.
• Authenticates automatically via Chrome browser cookies, bypassing the need for API keys.
• Facilitates multi-turn text chat using Gemini Flash, Pro, and Flash-Thinking models.
• Generates and edits images with 2x resolution upscaling and aspect ratio support.

ユースケース

• Creating and refining visual content through AI image generation and editing.
• Extracting insights and summaries from videos, documents, and web pages.
• Integrating Google Gemini's AI capabilities into applications or workflows via an MCP server.