MCP Telegram
Control Telegram using LLMs through the Model Context Protocol (MCP).
Connect Large Language Models to Telegram via the Model Context Protocol (MCP).
Built with Telethon, this server allows AI agents to interact with Telegram, enabling features like sending/editing/deleting messages, searching chats, managing drafts, downloading media, and more using the MTProto.
🚀 Getting Started
Prerequisites
- Python 3.10 or higher
uvInstall via the official uv guide.
Installation
Install the mcp-telegram CLI tool:
uv tool install mcp-telegram
⚙️ Usage
[!IMPORTANT] Please ensure you have read and understood Telegram's ToS before using this tool. Misuse of this tool may result in account restrictions.
The mcp-telegram command-line tool is your entry point.
mcp-telegram --help # See all commands
Login
First, authenticate with your Telegram account:
mcp-telegram login
This interactive command will prompt you for:
- API ID & API Hash: Obtain these from my.telegram.org/apps.
- Phone Number: Your Telegram-registered phone number (international format, e.g.,
+1234567890). - Verification Code: Sent to your Telegram account upon first login.
- 2FA Password: If you have Two-Factor Authentication enabled.
Your credentials are securely stored in the session file for future use.
[!WARNING] Keep your API credentials private and never share them publicly
[!NOTE] Use
mcp-telegram logoutto logout from current session ormcp-telegram clear-sessionto remove all stored session data.
Connect to the MCP server
To use MCP Telegram with MCP clients like Claude Desktop or Cursor, you'll need to configure the MCP server. The configuration process varies by client and operating system.
For detailed setup instructions, please refer to:
The configuration file should contain:
{
"mcpServers": {
"mcp-telegram": {
"command": "mcp-telegram" /* Use full path if client can't find the command (e.g. "/usr/local/bin/mcp-telegram"). See IMPORTANT section below for full path instructions. */,
"args": ["start"],
"env": {
"API_ID": "<your_api_id>",
"API_HASH": "<your_api_hash>"
}
}
}
}
[!Note] Configuration paths vary by OS and client. For example:
- macOS:
~/Library/Application Support/Claude/or~/.cursor/- Windows:
%APPDATA%\Claude\or%APPDATA%\Cursor\
[!IMPORTANT] If your client cannot execute
mcp-telegramdespite it being accessible in the terminal, try using the full path to the executable. You can find this by runningwhich mcp-telegram(macOS/Linux) orwhere mcp-telegram(Windows) in your terminal. Replace thecommandvalue in the configuration with the full path.
After saving the configuration file, restart your application.
🧰 Available Tools
Here's a comprehensive list of tools you can use to interact with Telegram through MCP:
📨 Messaging Tools
| Tool | Description |
|---|---|
send_message | ✉️ Send text messages or files to any user, group, or channel |
edit_message | ✏️ Modify content of previously sent messages |
delete_message | 🗑️ Remove one or multiple messages |
get_messages | 📜 Retrieve message history with advanced filtering options |
🔍 Search & Navigation
| Tool | Description |
|---|---|
search_dialogs | 🔎 Find users, groups, and channels by name or username |
message_from_link | 🔗 Access specific messages using Telegram links |
📝 Draft Management
| Tool | Description |
|---|---|
get_draft | 📋 View current message draft for any chat |
set_draft | ✍️ Create or clear message drafts |
📂 Media Handling
| Tool | Description |
|---|---|
media_download | 📸 Download photos, videos, and documents from messages |
[!Note] For detailed parameter information and example use cases, run
mcp-telegram toolsin your terminal.
🛠️ Troubleshooting
Database Locked Errors
Running multiple mcp-telegram instances using the same session file can cause database is locked errors due to Telethon's SQLite session storage. Ensure only one instance uses a session file at a time.
If you need to stop potentially stuck processes:
- macOS / Linux:
pkill -f "mcp-telegram" - Windows:
taskkill /F /IM mcp-telegram.exe /T(Check Task Manager for the exact process name)
🤝 Contributing
We welcome contributions! If you'd like to help improve MCP Telegram, please feel free to submit issues, feature requests, or pull requests. Your feedback and contributions help make this project better for everyone.
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
Related Servers
Gossiper Shopify Admin MCP Server
Control Shopify Admin tasks with agents or via prompt. Ultra slim integration, fast and secure.
Human-in-the-Loop
Allows AI assistants to ask questions to humans via Discord.
Agent Communication MCP Server
Enables room-based messaging between multiple agents.
Telegram
A server for interacting with Telegram via the MTProto API, requiring API credentials.
Lara Translate
Translate text with language detection, context-awareness, and translation memories using the Lara Translate API.
WhatsApp (TypeScript/Baileys)
Connects a personal WhatsApp account to an AI agent using the WhatsApp Web multi-device API.
Yazio MCP
MCP server for accessing Yazio user & nutrition data (unofficial)
Sinch
Interact with Sinch APIs for communication services like conversation, email, verification, and voice.
MCP-Lingvanex-Translate
Lingvanex MCP Server Cloud API – A Model Context Protocol server that provides fast and accurate text translation using the Lingvanex Cloud API. Supports 100+ languages and integrates seamlessly with Claude Desktop and other MCP-compatible clients.
Unipile
Access and manage messages from multiple platforms using the Unipile API.