monteslu
MCP Servermonteslupublic

vibe eyes client

Client library for integrating browser games with Vibe Eyes MCP debug server

Repository Info

2
Stars
1
Forks
2
Watchers
0
Issues
JavaScript
Language
-
License

About This Server

Client library for integrating browser games with Vibe Eyes MCP debug server

Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.

Documentation

Vibe Eyes Client

A lightweight client library to integrate browser games with the Vibe Eyes MCP debug server for real-time debugging, visualization, and analysis.

This allows AI to SEE the game it's working on in real time!

Happy Face

Features

  • Automatic canvas screenshot capture and streaming
  • Console log and error collection with timestamps
  • Global error and unhandled promise rejection handling
  • SVG visualization display in a dedicated debug window
  • Complete debug stats with SVG size measurements
  • Minimal performance impact on games
  • Robust error handling with graceful connection recovery
  • Multiple build formats (UMD, ESM, IIFE)

What's New in 1.1.0

  • Disconnected SVG Display: Debug window now works even when not connected to server
  • Connection Status Visualization: Show real-time connection status with visual feedback
  • Smart Window Positioning: Position debug window relative to game window (right, left, top, bottom)
  • Responsive Defaults: Debug window size defaults to 75% of game window dimensions
  • Improved Error Handling: Better handling of window closures and reconnection scenarios

Installation

npm install vibe-eyes-client

Or include directly in your HTML:

<script src="https://unpkg.com/vibe-eyes-client/dist/vibe-eyes.min.js"></script>

Usage

Basic Integration

// Initialize with default settings (auto-connects to http://localhost:8869)
// Available globally when using the script tag
// The client will automatically start capturing once connected
initializeVibeEyes();

// Or use the existing client instance directly
window.VibeEyesClient.initialize();

Custom Configuration

// Initialize with custom settings (when included via script tag)
initializeVibeEyes({
  serverUrl: 'http://your-debug-server:8869',
  captureDelay: 2000,   // Screenshot every 2 seconds
  maxLogs: 50,          // Store more logs
  canvasId: 'my-canvas' // Specific canvas to capture
});

// Or when using as a module
import { initializeVibeEyes } from 'vibe-eyes-client';

initializeVibeEyes({
  serverUrl: 'http://your-debug-server:8869',
  captureDelay: 2000,
  canvasId: 'game-canvas'
});

Manual Control

// Get the client instance
const client = window.VibeEyesClient;

// Explicitly stop/restart capturing if needed
client.stopCaptureLoop();
client.startCaptureLoop();

Displaying SVG Visualizations

Vibe Eyes MCP server sends back SVG visualizations that you can display in a dedicated debug window:

// Get the client from initialization
const client = initializeVibeEyes();

// Enable SVG display - opens a new debug window with SVG and stats
client.enableSvgDisplay();

// You can optionally provide a custom container
client.enableSvgDisplay({
  container: '#my-custom-container' // Optional existing container element
});

// Configure the debug window position and size (all options are optional)
const client = initializeVibeEyes({
  serverUrl: 'http://localhost:8869',
  debugWindow: {
    // All debugWindow properties are optional with sensible defaults
    width: 500,                // Optional: Width in pixels (default: 75% of game window width)
    height: 600,               // Optional: Height in pixels (default: 75% of game window height)
    position: 'right'          // Optional: Position relative to game window (default: 'right')
    // Possible positions: 'right', 'left', 'top', 'bottom', 'detached'
  }
});

// Toggle the display on/off
client.toggleSvgDisplay();

// Disable the display (closes the debug window)
client.disableSvgDisplay();

The debug window shows:

  • The SVG visualization at the top
  • Complete response statistics at the bottom, including SVG size
  • Updates in real-time as new data arrives from the server

Configuration Options

All configuration options are optional and have sensible defaults.

Client Initialization Options

OptionDefaultDescription
serverUrl'http://localhost:8869'URL of the Vibe Eyes MCP server
captureDelay1000Milliseconds between captures
maxLogs10Maximum stored console logs
maxErrors10Maximum stored error logs
autoConnecttrueConnect on initialization
canvasIdnullID of specific canvas to capture (null = auto-detect)
debugWindowObjectConfiguration for the debug window (see below)

SVG Display Options

OptionDefaultDescription
containernullElement or selector for SVG container (creates popup window if null)

Debug Window Options

OptionDefaultDescription
widthnullWidth of the debug window in pixels (null = 75% of game window width)
heightnullHeight of the debug window in pixels (null = 75% of game window height)
position'right'Position relative to the game window: 'right', 'left', 'top', 'bottom', or 'detached'

Build Formats

The following build formats are available in the dist/ directory:

  • vibe-eyes.min.js - Minified UMD build for most use cases
  • vibe-eyes.js - Unminified UMD build for debugging
  • vibe-eyes.iife.js - IIFE build with globals for direct browser use
  • vibe-eyes.esm.js - ES Module for modern bundlers and environments
  • Vibe Eyes MCP Server - The companion server that processes debug data and generates visualizations

License

ISC

Quick Start

1

Clone the repository

git clone https://github.com/monteslu/vibe-eyes-client
2

Install dependencies

cd vibe-eyes-client
npm install
3

Follow the documentation

Check the repository's README.md file for specific installation and usage instructions.

Repository Details

Ownermonteslu
Repovibe-eyes-client
LanguageJavaScript
License-
Last fetched8/10/2025

Recommended MCP Servers

💬

Discord MCP

Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.

integrationsdiscordchat
🔗

Knit MCP

Connect AI agents to 200+ SaaS applications and automate workflows.

integrationsautomationsaas
🕷️

Apify MCP Server

Deploy and interact with Apify actors for web scraping and data extraction.

apifycrawlerdata
🌐

BrowserStack MCP

BrowserStack MCP Server for automated testing across multiple browsers.

testingqabrowsers

Zapier MCP

A Zapier server that provides automation capabilities for various apps.

zapierautomation