Control Telegram using LLMs through the Model Context Protocol (MCP).
Details
Author
dryeab
GitHub stars
244
Downloads
840
Categories
Communication, Other, AI
Jump to
- Send, edit, and delete messages in any chat
- Search users, groups, and channels by name
- View, set, and clear message drafts
- Download photos, videos, and documents from messages
- Retrieve message history with advanced filtering
- Access specific messages via Telegram links
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
Install the tool with uv tool install mcp-telegram, then authenticate by running mcp-telegram login and providing your API ID and API Hash from my.telegram.org, phone number, and verification code. Finally, configure your MCP client (e.g., Claude Desktop) to use the command mcp-telegram start with the API_ID and API_HASH environment variables.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
<div align="center">
<img src="logo.png" alt="MCP Telegram Logo" width="150"/>
<h2 style="margin-top: 0">Enable LLMs to control your Telegram</h2>
</div>
<div align="center">
<a href="https://github.com/dryeab/mcp-telegram/stargazers"><img src="https://img.shields.io/github/stars/dryeab/mcp-telegram?style=social" alt="GitHub stars"></a>
<a href="https://badge.fury.io/py/mcp-telegram"><img src="https://badge.fury.io/py/mcp-telegram.svg" alt="PyPI version"></a>
<a href="https://x.com/dryeab"><img src="https://img.shields.io/twitter/follow/dryeab?style=social" alt="Twitter Follow"></a>
</div>
<h3></h3>
**Connect Large Language Models to Telegram via the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction).**
Built with [Telethon](https://github.com/LonamiWebs/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](https://core.telegram.org/mtproto).
---
<details>
<summary><strong>Table of Contents</strong></summary>
- [🚀 Getting Started](#-getting-started)
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [⚙️ Usage](#️-usage)
- [Login](#login)
- [Connect to the MCP server](#connect-to-the-mcp-server)
- [🧰 Available Tools](#-available-tools)
- [📨 Messaging Tools](#-messaging-tools)
- [🔍 Search & Navigation](#-search--navigation)
- [📝 Draft Management](#-draft-management)
- [📂 Media Handling](#-media-handling)
- [🛠️ Troubleshooting](#️-troubleshooting)
- [🤝 Contributing](#-contributing)
- [📝 License](#-license)
</details>
---
## 🚀 Getting Started
### Prerequisites
- Python 3.10 or higher
- [`uv`](https://github.com/astral-sh/uv) Install via the [official uv guide](https://github.com/astral-sh/uv#installation).
### Installation
Install the `mcp-telegram` CLI tool:
```bash
uv tool install mcp-telegram
```
## ⚙️ Usage
> [!IMPORTANT]
> Please ensure you have read and understood Telegram's [ToS](https://telegram.org/tos) before using this tool. Misuse of this tool may result in account restrictions.
The `mcp-telegram` command-line tool is your entry point.
```bash
mcp-telegram --help # See all commands
```
### Login
First, authenticate with your Telegram account:
```bash
mcp-telegram login
```
This interactive command will prompt you for:
- **API ID & API Hash:** Obtain these from [my.telegram.org/apps](https://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 logout` to logout from current session or `mcp-telegram clear-session` to 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:
- [Claude Desktop MCP Setup Guide](https://modelcontextprotocol.io/quickstart/user)
- [Cursor MCP Documentation](https://docs.cursor.com/context/model-context-protocol)
The configuration file should contain:
```json
{
"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-telegram` despite it being accessible in the terminal, try using the full path to the executable. You can find this by running `which mcp-telegram` (macOS/Linux) or `where mcp-telegram` (Windows) in your terminal. Replace the `command` value 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 tools` in 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.
<details>
<summary>Force-Stopping Existing Processes</summary>
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)
</details>
## 🤝 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](LICENSE) file for details.
---
<div align="center">
<p>Made with ❤️ by <a href="https://x.com/dryeab">Yeabsira Driba</a></p>
</div>
No reviews yet — be the first
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
Social sign-in isn’t configured yet. You can still create an account with email below, or ask an admin to add Google/GitHub/Discord OAuth credentials.
Sequential Thinking is an MCP server that provides a tool for dynamic and reflective problem-solving through a structured, step-by-step thinking process. It is…
Filesystem is a Node.js server that implements the Model Context Protocol (MCP) for filesystem operations. It enables AI assistants to read, write, and manage…