# link-mcp-server

MCP server for extracting UI, text, screenshots, and requirements from public links (including Axure prototypes). Designed specifically to empower AI coding assistants (like Cursor) with frontend context.

## Features

- **Screenshot Capture**: Automatically takes full-page screenshots of the provided link.
- **Frontend Analysis**: Generates structured Markdown reports tailored for frontend development:
  - Inferred States (React/Vue state variables)
  - Components & Interactions
  - API Integration needs
  - Change Points (mapping annotations to DOM elements)
- **DOM Extraction**: Extracts visible text blocks and image URLs.
- **Axure Support**: Specially optimized for Axure share links to extract marker annotations and requirement changes.
- **Works with MCP**: Fully compatible with Model Context Protocol clients (Cursor, Claude Desktop, etc.) via stdio.

## Requirements

- Node.js >= 18
- npm >= 9

## Quick Start

```bash
npm install
npx playwright install chromium
npm run build
npm start
```

## MCP Tools

### 1) `analyze_link_for_frontend`

Analyze a public link (like Axure) for frontend development. Returns a screenshot and a frontend-focused markdown analysis.

**Input:**
```json
{
  "url": "https://vscn2w.axshare.com/?id=ul0dre&p=3_5%E9%9C%80%E6%B1%82%E6%9B%B4%E6%96%B0&sc=3"
}
```

**Output:**
Returns two blocks to the AI client:
1. An `image` block containing the full-page screenshot.
2. A `text` block containing the Markdown analysis report.

### 2) `link_health`

Health check of runtime.

## Use in Cursor

Add to MCP config:

```json
{
  "mcpServers": {
    "link-mcp-server": {
      "command": "npx",
      "args": ["-y", "link-mcp-server"]
    }
  }
}
```

## Publish to npm

```bash
npm login
npm publish --access public
```