Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/DLHellMe/telegram-mcp-server below:

DLHellMe/telegram-mcp-server: Powerfull Telegram MCP for Claude Desktop to scrape and analyze Telegram content.

A powerful MCP (Model Context Protocol) server that enables Claude to interact with Telegram channels and groups. This server provides both web scraping and direct API access to Telegram content.

• 100x faster than web scraping
• Direct access via Telegram's MTProto protocol
• Search functionality within channels
• Access to private channels you're a member of
• Complete message metadata (views, reactions, forwards)
• Persistent sessions - authenticate once
• No browser automation needed
• Unlimited post retrieval by default

• No API credentials required
• Browser-based scraping with Puppeteer
• Authentication support for restricted content
• Visual media extraction
• Suitable for quick, anonymous access

• Node.js 18.0.0 or higher
• Chrome/Chromium (for web scraping mode)
• Telegram API credentials (for API mode) - Get them here

1. Clone this repository:

git clone https://github.com/DLHellMe/telegram-mcp-server.git
cd telegram-mcp-server

1. Install dependencies:

1. Copy the example environment file:

1. Edit .env and add your configuration:

   • For API mode: Add your TELEGRAM_API_ID and TELEGRAM_API_HASH
   • For web scraping: Default settings work out of the box

2. Build the project:

1. Go to https://my.telegram.org
2. Log in with your phone number
3. Click "API development tools"
4. Create a new application
5. Copy your api_id and api_hash to the .env file

Add this to your Claude Desktop config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "telegram-scraper": {
      "command": "node",
      "args": ["/absolute/path/to/telegram-mcp-server/dist/index.js"],
      "env": {
        "TELEGRAM_API_ID": "your_api_id",
        "TELEGRAM_API_HASH": "your_api_hash"
      }
    }
  }
}

After configuration, restart Claude Desktop. The Telegram tools will be available in Claude.

1. telegram_api_login - Authenticate with Telegram (first time only)

   Use telegram_api_login to connect to Telegram
   

2. api_scrape_channel - Scrape channel posts (unlimited by default)

   Use api_scrape_channel with url="https://t.me/channelname"
   

   Or with a limit:

   Use api_scrape_channel with url="https://t.me/channelname" and max_posts=50
   

3. api_search_channel - Search within a channel

   Use api_search_channel with url="https://t.me/channelname" and query="keyword"
   

1. scrape_channel - Scrape public channels

   Use scrape_channel with url="https://t.me/channelname"
   

2. telegram_login - Login for restricted content

   Use telegram_login with phone="+1234567890"
   

Session data and cookies are stored in platform-specific directories:

• Windows: %APPDATA%\telegram-mcp-data
• macOS: ~/Library/Application Support/telegram-mcp-data
• Linux: ~/.config/telegram-mcp-data

You can override this with the TELEGRAM_DATA_PATH environment variable.

• Never commit your .env file - it contains sensitive API credentials
• API credentials are personal - each user needs their own
• Session files contain authentication data - keep them secure
• Use the .gitignore file to prevent accidental commits

# Run in development mode
npm run dev

# Build the project
npm run build

# Watch for changes
npm run watch

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Submit a pull request

MIT License - see LICENSE file for details

Built with:

• Model Context Protocol SDK
• GramJS - Telegram client library
• Puppeteer - Browser automation

This tool is for educational and research purposes. Please respect Telegram's Terms of Service and the privacy of channel members. Always obtain permission before scraping private channels.

• "Not connected to Telegram API": Run telegram_api_login first
• Phone number format: Include country code (e.g., +1234567890)
• 2FA errors: Enter your 2FA password when prompted

• "No Chrome binary found": Install Chrome or Chromium
• Login issues: Ensure you're using the correct phone format
• Timeout errors: Increase BROWSER_TIMEOUT in .env

• Create an issue on GitHub for bugs
• Check existing issues before creating new ones
• Include error messages and logs when reporting issues

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4