Telegram

Sends Telegram notifications and collects user responses for MCP-based workflows

javascript

4

GitHub Stars

javascript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mobilevibe-telegram-mcp": {
      "command": "node",
      "args": [
        "path/to/telegram-mcp/build/index.js"
      ],
      "env": {
        "TELEGRAM_CHAT_ID": "your_chat_id",
        "TELEGRAM_BOT_TOKEN": "your_bot_token"
      }
    }
  }
}

You can use the Telegram MCP Server to send text notifications to a Telegram chat, wait for user responses, and integrate those interactions with MCP-compatible LLM applications. It’s useful for prompting humans to respond to model-generated tasks and for streaming feedback through a familiar chat interface.

How to use

You run the Telegram MCP Server as a local process and point your MCP client to it. When you send a notification, the server posts a message to your configured Telegram chat with an optional urgency level. You can then check for a user response and continue the workflow based on the reply.

Typical usage patterns include sending a notification about a task or decision point, waiting for a user reply, and feeding that reply back into your LLM workflow. The server is designed to integrate with Cline and other MCP-compatible MPC clients so you can orchestrate prompts and human-in-the-loop feedback across different tooling.

How to install

Prerequisites: you need Node.js 16 or higher, a Telegram bot token, and your Telegram chat ID.

From npm (recommended) you install the package globally:

npm install -g telegram-mcp

Configuration

You configure the server using environment variables. The following are required to run the server and connect to your Telegram chat.

Required environment variables

TELEGRAM_BOT_TOKEN: Your Telegram bot token

TELEGRAM_CHAT_ID: Your Telegram chat ID

Examples and integration snippets

To integrate with a Cline MCP settings file, you would run the server locally and point the MCP to the local command path with the required environment variables. The example below shows how the runtime entry looks in an MCP settings configuration.

Available tools

send_notification

Sends a notification message to the configured Telegram chat. Requires message, project, and optional urgency.

check_notification_response

Checks if the user has responded to a previously sent notification, with an optional timeout.