monteslu/vibe-eyes

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.

56
/ 100
Established

This project helps developers working on browser-based games and applications get real-time visual and debugging information into AI models. It captures what's displayed on your game's screen (the canvas), along with any console logs or errors, and sends it as a concise, vectorized image and text to your AI assistant. This means your AI can "see" and understand the visual state of your application as it's running, providing more accurate and relevant debugging help.

Available on npm.

Use this if you are a developer building browser games or applications and want your AI assistant to have a live, visual understanding of your app's state, alongside debugging information, to help you troubleshoot problems.

Not ideal if you need pixel-perfect image capture for graphics analysis, or if your application isn't browser-based and doesn't rely on a canvas element for its visuals.

game-development web-application-development front-end-debugging AI-assisted-development developer-tools
Maintenance 10 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

50

Forks

7

Language

JavaScript

License

MIT

Last pushed

Feb 04, 2026

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/monteslu/vibe-eyes"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.