telegram

This Telegram MCP server exposes a Model Context Protocol interface that lets AI assistants interact with the Telegram Bot API. It supports core operations such as sending messages, sending photos with optional captions, and deleting messages from chats. To use it, configure an MCP client to point at the telegram server entry (as shown in the example configuration) and invoke supported operations with the appropriate JSON payloads. The server handles the translation from MCP operations to Telegram Bot API calls, enabling your AI to send text, images, or manage messages within chats via standardized MCP messages.

Prerequisites:

• Node.js and npm installed
• Internet connection to install dependencies

Steps:

1. Clone or download the repository containing the Telegram MCP Server
2. Install dependencies

   npm install
   

3. Provide your Telegram Bot Token by creating a .env file (or set the env var in your runtime environment)

   TELEGRAM_BOT_TOKEN=your_bot_token_here
   

4. Build the TypeScript project (if applicable in your setup)

   npm run build
   

5. Start the server

   npm start
   

6. (Optional) Update MCP client configuration to point to the server, using the example below

   {
     "mcpServers": {
       "telegram": {
         "command": "node",
         "args": ["path/to/telegram-mcp-server/dist/telegram-mcp.js"],
         "env": {
           "TELEGRAM_BOT_TOKEN": "your_bot_token_here"
         }
       }
     }
   }
   

Notes and tips:

• Ensure the TELEGRAM_BOT_TOKEN is kept secure and not committed to version control.
• If you modify the server code or build outputs, update the path in the MCP client configuration accordingly.
• The server relies on the Telegram Bot API; make sure your bot has the necessary permissions for the actions you plan to perform (e.g., sending messages, sending photos, deleting messages).
• If you encounter network or API errors, check Telegram Bot API rate limits and verify that your bot token is valid.
• For debugging, run the server in a environment that prints logs to stdout/stderr to observe MCP payload handling and Telegram API responses.