# UpGrad LXP MCP Server

An MCP (Model Context Protocol) server that controls a Firefox browser via Playwright to automate navigating UpGrad's learning platform, extracting class transcripts, and downloading resources.

## Setup

```bash
npm install
npx playwright install firefox
```

## Usage

### With Claude Code / Claude Desktop

Add to your MCP configuration:

```json
{
  "mcpServers": {
    "upgrad-lxp": {
      "command": "npx",
      "args": ["tsx", "/path/to/upgrad-lxp-mcp/src/index.ts"],
      "env": {
        "UPGRAD_EMAIL": "your-email@example.com",
        "UPGRAD_PASSWORD": "your-password",
        "OUTPUT_DIR": "./output",
        "HEADLESS": "false"
      }
    }
  }
}
```

### Run directly

```bash
npm start
```

## Available Tools

| Tool | Description |
|------|-------------|
| `launch_browser` | Launch Firefox browser instance |
| `close_browser` | Close the browser |
| `login` | Log into UpGrad LXP |
| `check_login_status` | Check if currently logged in |
| `list_courses` | List available courses |
| `select_course` | Navigate into a course |
| `list_tracks` | List tracks/modules in a course |
| `select_track` | Navigate into a track |
| `list_past_classes` | List past classes in a track |
| `view_class_details` | Open a specific class's details |
| `extract_transcript` | Extract transcript from class details |
| `extract_resources` | Extract resource links from class details |
| `download_resource` | Download a resource file |
| `save_transcript` | Save transcript to disk |
| `screenshot` | Take a page screenshot |
| `get_page_content` | Get page text content |
| `navigate` | Navigate to a URL |
| `click` | Click an element |
| `scrape_all_past_classes` | Bulk scrape all past classes |

## Output Structure

```
output/
├── transcripts/     # Saved transcript files (.md, .txt, .json)
├── resources/       # Downloaded resource files (organized by class)
├── screenshots/     # Page screenshots
├── errors/          # Error screenshots for debugging
└── index.json       # Manifest from bulk scraping
```

## Selector Updates

The CSS selectors in `src/helpers/selectors.ts` are initial guesses. After first launch:

1. Run the browser in headed mode (`headless: false`)
2. Log in and navigate to the target pages
3. Use browser DevTools to inspect the actual DOM
4. Update `selectors.ts` with the real selectors