Vibe Eyes
Vibe-Eyes is an MCP server project that enables LLMs to 'see' what's happening in browser-based games and applications through vectorized canvas visualization and debugging information.
rating : 2.5 points
downloads : 40
What is the Vibe-Eyes MCP Server?
The Vibe-Eyes MCP Server is a lightweight tool that generates visualization and debugging information by capturing canvas elements, console logs, and errors in the browser and passes it to the language model through the model context protocol (MCP), helping developers debug more efficiently.How to use the Vibe-Eyes MCP Server?
Simply integrate the Vibe-Eyes client script into your browser game and configure the server address to start capturing and transmitting data. The language model can use the provided MCP tools to obtain the latest status.Applicable Scenarios
Suitable for developers who need to quickly diagnose problems in browser games or applications, especially when visual and code context need to be combined.Main Features
Canvas VisualizationAutomatically capture canvas elements in the browser and generate vectorized SVG images.
Real-time Debugging InformationCollect console logs, errors, and unhandled exceptions, including full stack information.
Model Context Protocol SupportPass data directly to the language model through MCP tools, enabling them to 'see' the state of the application.
Performance OptimizationUse efficient vectorization algorithms to reduce data size while ensuring image quality.
Advantages and Limitations
Advantages
Reduce the workload of manual screenshots and descriptions.
Provide comprehensive visual and code context.
Synchronize data in real-time to accelerate the debugging process.
Support integration with multiple language models.
Limitations
May affect the performance of some highly complex applications.
Depend on a stable WebSocket connection.
The vectorization accuracy is limited and may not fully restore the details of the original image.
How to Use
Install the Server
Clone the project code and install the dependencies.
Start the Server
Run the server to listen for WebSocket connections.
Integrate the Client
Add the Vibe-Eyes client script to your browser game.
Configure the MCP Tool
Ensure that the language model has registered the Vibe-Eyes MCP service.
Usage Examples
Case 1: Quickly Locate ErrorsWhen the game crashes, Vibe-Eyes captures the current screen and error information to help the model locate the problem faster.
Case 2: Assist in DevelopmentWhen developing new features, Vibe-Eyes can help you capture the current interface state and analyze it in combination with the code.
Frequently Asked Questions
Will Vibe-Eyes affect game performance?
How to ensure a stable WebSocket connection?
Can the vectorized image fully restore the original image?
Related Resources
GitHub Repository
Access the source code and documentation of Vibe-Eyes.
Client Documentation
Learn how to integrate the Vibe-Eyes client in the browser.
YouTube Video Tutorial
Watch a demonstration of how Vibe-Eyes works.
Featured MCP Services

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
141
4.5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
86
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
830
4.3 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
566
5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
754
4.8 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points