annotation-overlay-mcp
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.
README
Annotation Overlay MCP
DOM-aware visual annotation overlay for web feedback. Draw arrows, boxes, text, freehand strokes, click elements, and annotate text selections — all in one toolbar. Submit structured annotations to Claude Code via MCP.
6 interaction modes. Zero JS dependencies. Chrome Extension + MCP Server.
[Browser Page] ←→ [Chrome Extension] ←→ [MCP Server] ←→ [Claude Code]
overlay.js bridge.js HTTP + stdio read/clear tools
Quick Start
1. Install & Start MCP Server
git clone https://github.com/cc10143/annotation-overlay-mcp.git
cd annotation-overlay-mcp
npm install
npm start
# → HTTP server on port 3847 + MCP stdio transport connected
2. Load Chrome Extension
- Open
chrome://extensions - Enable Developer mode
- Click Load unpacked
- Select the
extension/directory
The overlay now auto-injects on every page. Press Ctrl+Shift+A to toggle the toolbar.
3. Configure Claude Code MCP
// ~/.claude/settings.json
{
"mcpServers": {
"annotation-overlay-mcp": {
"command": "node",
"args": ["D:/KaiFa/annotation-overlay/server/index.js"]
}
}
}
Or use the CLI:
claude mcp add annotation-overlay-mcp -- node D:/KaiFa/annotation-overlay/server/index.js
Usage
Annotation Workflow
- Open any page — the overlay auto-injects via Chrome extension
- Annotate — use any of the 6 tools to mark issues
- Submit — click Submit to send structured JSON to the MCP server
- Agent reads — Claude Code calls
read_annotations→ processes feedback - Page refreshes — extension auto-reinjects overlay → next round
Tools
| Tool | Label | How | DOM Link |
|---|---|---|---|
| Arrow | ➤ | Click & drag → arrow with comment | Element under arrowhead |
| Box | □ | Click & drag → rectangle with comment | Element under box center |
| Text | T | Click → floating text label | Element under click point |
| Freehand | ✎ | Click & drag → freeform drawing | Element under bbox center |
| Select | + | Hover highlights blue → click to pin numbered badge | Clicked element |
| TextSel | [ ] | Select page text → comment input at selection | Containing element |
Keyboard Shortcuts
| Key | Action |
|---|---|
Ctrl+Shift+A |
Toggle overlay |
Ctrl+Z |
Undo last annotation |
Escape |
Cancel drawing / close overlay |
Enter |
Confirm comment |
Shift+Enter |
Newline in comment |
Colors
5 preset colors: red #e94560, blue #4080f0, green #2ecc71, yellow #f1c40f, purple #9b59b6.
MCP Tools
read_annotations
Read all pending annotations. Each annotation includes:
{
"id": "uuid",
"type": "arrow | circle | text | freehand | select | textsel",
"comment": "user feedback text",
"selector": "div.card:nth-child(1) > button.btn-primary",
"fallbackSelectors": [
{ "type": "id", "value": "#submit-btn" },
{ "type": "cssPath", "value": "div.card:nth-child(1) > ..." },
{ "type": "contentHash", "value": "Buy Now-a3f8b2c1" }
],
"tagName": "BUTTON",
"classes": ["btn-primary"],
"elementText": "Buy Now",
"contentHash": "Buy Now-a3f8b2c1",
"position": { "start": {"x":100,"y":200}, "end": {"x":300,"y":400} },
"color": "#e94560"
}
clear_annotations
Clear all stored annotations. Call after processing feedback.
Selector Fallback Chain
When the agent regenerates the page, CSS selectors may break. Each annotation carries a fallback chain:
- id —
#element-id(most stable) - cssPath —
div.card:nth-child(1) > button.btn-primary - contentHash —
Buy Now-a3f8b2c1(first 40 chars of text + djb2 hash)
The agent should try each fallback in order when resolving elements after page changes.
Standalone Use (Without Extension)
The overlay can be injected into any page via script tag or browser console:
<script src="annotation-overlay.js"></script>
Or via Tandem evaluate / Playwright:
// Tandem
tandem_devtools_evaluate({ function: "..." }) // paste annotation-overlay.js contents
// Playwright
await page.evaluate(fs.readFileSync('annotation-overlay.js', 'utf-8'));
Public API:
__annotationOverlay.activate() // show toolbar
__annotationOverlay.deactivate() // hide overlay
__annotationOverlay.serialize() // → JSON string
__annotationOverlay.clear() // remove all annotations
__annotationOverlay.submit() // send to MCP server via direct fetch
Architecture
┌──────────────────────────────────────────────────────┐
│ annotation-overlay.js (src/, ~700 lines) │
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────────────┐ │
│ │ Toolbar │ │ Canvas │ │ DOM Bridge │ │
│ │ 6 tools │ │ 2D ctx │ │ elementFromPoint │ │
│ │ 5 colors│ │ DPR │ │ CSS selector gen │ │
│ │ Submit │ │ undo │ │ contentHash │ │
│ └────┬─────┘ └────┬─────┘ └────────┬─────────┘ │
│ │ │ │ │
│ └─────────────┴───────┬────────┘ │
│ │ │
│ ┌────────▼────────┐ │
│ │ Annotation Model│ │
│ │ + Serializer │ │
│ │ + Fallback │ │
│ └────────┬────────┘ │
└─────────────────────────────┼────────────────────────┘
│ postMessage
┌─────────────────────────────┼────────────────────────┐
│ Chrome Extension ▼ │
│ ┌──────────────┐ ┌──────────────┐ │
│ │ bridge.js │ │ service- │ │
│ │ (ISOLATED) │ │ worker.js │ │
│ │ inject + │ │ badge + │ │
│ │ relay │ │ relay │ │
│ └──────┬───────┘ └──────┬───────┘ │
└─────────┼──────────────────┼──────────────────────────┘
│ │ HTTP (port 3847)
┌─────────▼──────────────────▼──────────────────────────┐
│ MCP Server (Node.js, single process) │
│ ┌──────────────┐ ┌──────────────┐ │
│ │ Express API │ │ MCP stdio │ │
│ │ POST/GET/ │ │ read_ │ │
│ │ DELETE ann │ │ clear tools │ │
│ └──────┬───────┘ └──────┬───────┘ │
│ └────────┬─────────┘ │
│ ┌────────▼────────┐ │
│ │ In-memory Store│ │
│ └─────────────────┘ │
└────────────────────────────────────────────────────────┘
Comparison
| Annotation Overlay MCP | Vibe Annotations | Dongke-X/redline | |
|---|---|---|---|
| Drawing tools | 4 (arrow/box/text/freehand) | None | Full HTML editor |
| Click-to-select | Yes (+ badge) | Yes | Full edit |
| Text selection annotation | Yes | No | No |
| MCP automation | Yes (stdio) | Yes (SSE/HTTP) | No (file-based) |
| Selector fallback | id→cssPath→contentHash | source maps | id→cssPath→contentHash |
| License | MIT | PolyForm Shield | Apache 2.0 |
| Dependencies | 3 (Express + cors + MCP SDK) | Many (WXT, etc.) | Many (React, etc.) |
Configuration
| Env Var | Default | Description |
|---|---|---|
ANNO_PORT |
3847 |
HTTP server port |
License
MIT — Copyright (c) 2026 gaogao
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.