About MCP Communicator (Telegram)
MCP Communicator (Telegram) is an MCP server that lets an AI agent communicate with a user through a Telegram bot. It can ask questions and wait for replies, send notifications, share files, and send project zip archives. It suits developers who want agents to reach them away from the desk.
Key features
- 01Ask questions through Telegram and await replies
- 02Send notifications that need no response
- 03Send files to the user via Telegram
- 04Zip projects respecting .gitignore patterns
- 05Chat ID validation for incoming messages
Use cases
- 01Asking the user for confirmation or input during an agent task
- 02Receiving a Telegram notification when a task completes
- 03Sending project archives or generated files to a phone
MCP support
This project is an MCP server that provides ask_user, notify_user, send_file and zip_project tools to MCP clients, enabling interaction with users over Telegram.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Communicator (Telegram)
An MCP server that enables communication with users through Telegram. This server provides tools to interact with users via a Telegram bot, including asking questions, sending notifications, sharing files, and creating project archives.
Installation
Via npm (global)
npm install -g mcp-communicator-telegram
Via npx (on-demand)
npx mcptelegram
To get your Telegram chat ID:
npx mcptelegram-chatid
Features
- Ask questions to users through Telegram
- Send notifications to users (no response required)
- Send files to users via Telegram
- Create and send project zip files (respecting .gitignore)
- Receive responses asynchronously (waits indefinitely for response)
- Support for reply-based message tracking
- Secure chat ID validation
- Error handling and logging
Prerequisites
- Node.js (v14 or higher)
- A Telegram bot token (obtained from @BotFather)
- Your Telegram chat ID (can be obtained using the included utility)
Installation
- Clone the repository:
git clone https://github.com/qpd-v/mcp-communicator-telegram.git
cd mcp-communicator-telegram
- Install dependencies:
npm install
-
Create a Telegram bot:
- Open Telegram and search for @BotFather
- Send
/newbotand follow the instructions - Save the bot token you receive
-
Get your chat ID:
- Copy
.env.exampleto.env - Add your bot token to the
.envfile:TELEGRAM_TOKEN=your_bot_token_here - Run the chat ID utility:
npm run build node build/get-chat-id.js - Send any message to your bot
- Copy the chat ID that appears in the console
- Add the chat ID to your
.envfile:TELEGRAM_TOKEN=your_bot_token_here CHAT_ID=your_chat_id_here
- Copy
Configuration
Add the server to your MCP settings file (usually located at %APPDATA%\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json on Windows):
{
"mcpServers": {
"mcp-communicator-telegram": {
"command": "node",
"args": ["path/to/mcp-communicator-telegram/build/index.js"],
"env": {
"TELEGRAM_TOKEN": "your_bot_token_here",
"CHAT_ID": "your_chat_id_here"
}
}
}
}
Available Tools
ask_user
Asks a question to the user via Telegram and waits for their response.
Input Schema:
{
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "The question to ask the user"
}
},
"required": ["question"]
}
Example usage:
const response = await use_mcp_tool({
server_name: "mcp-communicator-telegram",
tool_name: "ask_user",
arguments: {
question: "What is your favorite color?"
}
});
notify_user
Sends a notification message to the user via Telegram (no response required).
Input Schema:
{
"type": "object",
"properties": {
"message": {
"type": "string",
"description": "The message to send to the user"
}
},
"required": ["message"]
}
Example usage:
await use_mcp_tool({
server_name: "mcp-communicator-telegram",
tool_name: "notify_user",
arguments: {
message: "Task completed successfully!"
}
});
send_file
Sends a file to the user via Telegram.
Input Schema:
{
"type": "object",
"properties": {
"filePath": {
"type": "string",
"description": "The path to the file to send"
}
},
"required": ["filePath"]
}
Example usage:
await use_mcp_tool({
server_name: "mcp-communicator-telegram",
tool_name: "send_file",
arguments: {
filePath: "path/to/file.txt"
}
});
zip_project
Creates a zip file of a project directory (respecting .gitignore patterns) and sends it to the user via Telegram.
Input Schema:
{
"type": "object",
"properties": {
"directory": {
"type": "string",
"description": "Directory to zip (defaults to current working directory)"
}
},
"required": []
}
Example usage with default directory (current working directory):
await use_mcp_tool({
server_name: "mcp-communicator-telegram",
tool_name: "zip_project",
arguments: {}
});
Example usage with specific directory:
await use_mcp_tool({
server_name: "mcp-communicator-telegram",
tool_name: "zip_project",
arguments: {
directory: "/path/to/your/project"
}
});
Features:
- Creates a zip file named
[project-name]-project.zipbased on the directory name - Can zip any specified directory or the current working directory
- Respects .gitignore patterns
- Maintains correct file paths in the archive
- Automatically cleans up the zip file after sending
- Handles files up to 2GB in size
Development
Build the project:
npm run build
Run in development mode:
npm run dev
Watch for changes:
npm run watch
Clean build directory:
npm run clean
Security
- The server only responds to messages from the configured chat ID
- Environment variables are used for sensitive configuration
- Message IDs are used to track question/answer pairs
- The bot ignores messages without proper context
License
ISC
Author
qpd-v
Version
0.2.1 # Major version bump for new features: notify_user, send_file, and zip_project tools
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.