Enables DOM-aware visual annotation of web pages with drawing tools and element selection, submitting structured annotations to Claude Code via MCP for automated feedback processing.
Enables Claude to draw on a live tldraw canvas from prompts, with real-time visualization in a browser. Provides tools for creating, updating, deleting shapes and retrieving canvas state.
Enables creating and refining pencil-style drawings as layered HTML Canvas snippets through natural language descriptions, using classical construction methodology.
Provides a collaborative SVG canvas that allows Claude to create, read, and manipulate graphics in real-time through a browser-based Fabric.js editor. It enables seamless bidirectional interaction between the AI and user for visual tasks like UI prototyping, diagramming, and template management.
Enables annotating SVG paper figures in the browser by picking elements or drawing regions, and feeds those annotations back to Claude via MCP so it can edit the underlying SVG or generation scripts, with automatic page refresh on changes.