MCP Hub
Back to servers

ui-annotator-mcp

Annotates any web page with hover labels for AI assistants — zero extensions, any browser

Registry
Updated
Mar 20, 2026

Quick Install

npx -y @mcpware/ui-annotator

UI Annotator MCP

npm version license GitHub stars GitHub forks

See what every UI element is called — in any browser, zero extensions.

An MCP server that adds interactive hover annotations to any web page. Open a proxied URL, hover any element, see its name. Tell your AI assistant "make the sidebar wider" — it knows exactly what you mean.

Demo

The Problem

When reviewing a web UI with an AI coding assistant, the hardest part isn't the code change — it's describing which element you want changed.

"That thing on the left... the second row... no, the one with the icon..."

You don't know what it's called. The AI doesn't know what you're pointing at. You waste time on miscommunication instead of shipping.

The Solution

Open your page through the annotator proxy. Hover any element — instantly see its name, CSS selector, and dimensions. Now you both speak the same language.

# Start the MCP server
npx @mcpware/ui-annotator

# Open in ANY browser
http://localhost:7077/localhost:3847

That's it. No browser extensions. No code changes. No setup. Works in Chrome, Firefox, Safari, Edge — any browser.

How It Works

Your app (localhost:3847)
        │
        ▼
┌─────────────────────┐
│  UI Annotator Proxy  │ ← Reverse proxy on port 7077
│  (MCP Server)        │
└─────────────────────┘
        │
        ▼
Proxied page with hover annotations injected
        │
        ├──► User sees: hover overlay + tooltip with element names
        └──► AI sees: structured element data via MCP tools

The proxy fetches your page, injects a lightweight annotation script, and serves it back. The script scans the DOM, identifies named elements, and reports them to the MCP server. Your AI assistant queries the server to understand what's on the page.

Features

Hover Annotations

Hover any element to see:

  • Element name (pink) — the human-readable identifier
  • CSS selector (monospace) — the technical reference
  • Content preview — what text the element contains
  • Dimensions — width × height in pixels

Inspect Mode

Click the Inspect button in the toolbar (or let your AI toggle it). In inspect mode:

  • Click any element → copies its name to clipboard
  • All page interactions are paused (clicks don't trigger buttons/links)
  • Click Inspect again to return to normal mode

Collapsible Toolbar

The toolbar sits at the top center of the page showing:

  • Inspect toggle button
  • Element count
  • Helpful subtitle explaining what to do
  • Collapse button (▲) to minimize when not needed

MCP Tools for AI

ToolWhat it does
annotate(url)Returns proxy URL for user to open in any browser
get_elements()Returns all detected UI elements with names, selectors, positions
highlight_element(name)Flash-highlights a specific element so user can confirm
rescan_elements()Force DOM rescan after page changes
inspect_mode(enabled)Toggle inspect mode remotely

Why Not Just Use DevTools?

Browser DevToolsUI Annotator
Target userFrontend developers who know the DOMAnyone — QA, PM, designer, junior dev
Learning curveNeed to understand DOM tree, CSS selectors, box modelHover and read — zero learning
Communication"The div.flex.gap-4 inside the second child of...""The sidebar"
LanguageCSS/HTML technical termsHuman-readable names
SetupTeach people to open DevTools + navigate the DOMOpen a URL
AI integrationNone — AI can't see what you're inspectingMCP — AI sees the same element names you do

DevTools is for debugging. UI Annotator is for communication — giving humans and AI a shared vocabulary for UI elements.

Why Not Use Existing Tools?

ToolApproachWhy we're different
MCP PointerChrome extension + MCP serverRequires Chrome extension. Click-to-inspect, no hover overlay.
Agentationnpm package embedded in your appRequires code changes. React 18+ dependency. Not zero-config.
Cursor Visual EditorBuilt-in IDE browserOnly works inside Cursor IDE.
Windsurf PreviewsBuilt-in IDE browserOnly works inside Windsurf IDE.
Chrome DevTools MCPProgrammatic DOM access for AIAI can inspect, but humans don't see visual annotations.
VisBugChrome extension for visual editingNo MCP integration. No AI connection. Chrome only.
Marker.io / BugHerdSaaS visual feedback widgetsNot MCP. Paid. For bug reporting, not AI-assisted development.

Feature Comparison

FeatureUI AnnotatorMCP PointerAgentationCursorChrome DevTools MCP
Visual hover annotationYesNoPartialYes (IDE only)No
Shows element namesYesYesYesNo (high-level)Programmatic
Shows dimensionsYesYesYes (Detailed)YesProgrammatic
MCP serverYesYesYesNoYes
Zero browser extensionsYesNoYesN/ANo
Zero code changesYesYesNoN/AYes
Any browserYesChrome onlyDesktop onlyCursor onlyChrome only
Zero dependenciesYesChrome extReact 18+CursorChrome
Click to copy element nameYesNoNoNoNo

Architecture

Zero external dependencies

  • Reverse proxy: Node.js built-in http module
  • MCP server: @modelcontextprotocol/sdk (stdio transport)
  • Communication: HTTP POST (browser → server) + GET polling (server → browser)
  • No WebSocket, no Express, no browser extension

How the proxy works

  1. User requests localhost:7077/localhost:3847
  2. Proxy fetches http://localhost:3847
  3. For HTML responses:
    • Injects fetch() / XMLHttpRequest interceptor (rewrites API paths through proxy)
    • Rewrites href="/..." and src="/..." attributes to route through proxy
    • Injects annotation script before </body>
  4. For non-HTML (CSS, JS, images): passes through directly
  5. Strips Content-Security-Policy headers to allow injected script

How annotation works

  1. Script scans DOM for elements with id, class, semantic roles, or interactive roles
  2. On hover: positions overlay border (follows border-radius) + positions tooltip (always within viewport)
  3. Reports all detected elements to server via POST /__annotator/elements
  4. Polls GET /__annotator/commands every second for server instructions (highlight, rescan, inspect toggle)
  5. MutationObserver auto-rescans when DOM changes

Quick Start

With Claude Code

# Add as MCP server
claude mcp add ui-annotator -- npx @mcpware/ui-annotator

# Then in conversation:
# "Annotate my app at localhost:3847"
# → AI returns proxy URL, you open it, hover elements, discuss changes by name

Manual

npx @mcpware/ui-annotator
# Proxy starts on http://localhost:7077
# Open http://localhost:7077/localhost:YOUR_PORT

Environment Variables

VariableDefaultDescription
UI_ANNOTATOR_PORT7077Port for the proxy server

License

MIT

Reviews

No reviews yet

Sign in to write a review