This bridges visual UI review and AI-assisted fixes by letting you click elements in the browser, leave comments like "this button should be blue," then having your AI agent read those annotations via MCP and fix the underlying code. The Python server exposes 10 tools over stdio including get_annotated_reviews (returns CSS selectors, DOM paths, computed styles, accessibility metadata), resolve_review, and get_pending_work. A web component drops into any framework to render the review panel and annotation UI. Reviews live in SQLite inside your project. You get threaded replies, tag filtering, hover markers on annotated elements, and keyboard shortcuts. Works with Claude Code, Cursor, or any MCP-compatible agent that can read structured feedback and modify source files.
claude mcp add --transport stdio io.github.0ics-srls-ui-ticket-mcp uvx ui-ticket-mcp