Command Claude Code
A command that asks a vision tool to analyse a local image using a natural-language question.
An MCP (Model Context Protocol) server based on any vision model compatible with the Anthropic Messages protocol, providing 7 visual tools — general image analysis, UI-to-code, OCR, error diagnosis, chart understanding, data visualization analysis, and UI comparison. Compatible with Claude Code and any MCP client. Simply provide your model API endpoint, key, and model ID to get ready-to-use visual capabilities.
Command Claude Code
A command that asks a vision tool to analyse a local image using a natural-language question.
Command Claude Code
A command for analysing charts and other data visualisations, including trends, unusual values, and business-relevant findings.
Command Claude Code
A command for interpreting technical diagrams such as architecture drawings, flowcharts, UML diagrams, and database relationship diagrams.
Command Claude Code
A command for comparing two user-interface screenshots and listing their visual differences by severity.
Command Claude Code
A command for diagnosing error screenshots with a vision MCP server. It examines stack traces, console output, or error dialogs in an image and suggests fixes.
Command Claude Code
A command that extracts all visible text from a screenshot while preserving its original layout and structure. OCR, or optical character recognition, is the process of reading text in images.
Command Claude Code
A command that turns a user-interface screenshot into code or a written design description. A user interface is the visible part of an application that people interact with.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: