Get the latest tech news
Open source AI agent helper to let it SEE what its doing
description: "An MCP server that enables LLMs to 'see' what's happening in browser-based games and applications through vectorized canvas visualization and debug information. - G...
Vibe-Eyes uses a client-server architecture where a lightweight browser client captures canvas content and debug information, sends it to a Node.js server via WebSockets, which then vectorizes the images into compact SVG representations and makes them available to LLMs through the Model Context Protocol (MCP). A lightweight client runs in the browser game/application The client captures canvas snapshots, console logs/errors, and unhandled exceptions Data is sent to the Vibe-Eyes server via WebSocket (avoiding CORS issues) The server vectorizes the canvas images and stores them with the debug information LLMs connect via the Model Context Protocol to access the latest data LLMs can "see" what's happening and help debug issues with full context The browser client is designed to minimize impact on application performance Creating canvas data URLs can be CPU-intensive, so capturing frequency is configurable WebSocket transport avoids CORS issues common in cross-domain setups The server processes images sequentially to prevent overload SVG vectorization balances visual accuracy with size optimization
Or read this on Hacker News