telegram-mcp
A minimal Model Context Protocol server for interacting with Telegram bots via MTProto. It provides simple tools to send messages and retrieve chat history while serving as an easy-to-extend reference for developers.
README
telegram-mcp
A minimal MCP server for Telegram bot interaction via MTProto — intentionally simple, easy to read, and easy to extend.
Looking for a full-featured Telegram MCP server? Check out chigwell/telegram-mcp — 60+ tools covering messaging, groups, contacts, media, admin, and more.
This project takes a different approach: two tools, ~150 lines of server code, zero complexity. It's a clean starting point for anyone who wants to understand how MCP servers work with Telegram, or who only needs basic bot messaging without the overhead of a full client.
Why this exists
- Learning reference — Read the entire server in 5 minutes
- Fork-friendly — Add exactly the tools you need, nothing you don't
- Minimal dependencies — Just Telethon, MCP SDK, and python-dotenv
Tools
| Tool | Description |
|---|---|
send_message |
Send a message to a Telegram bot and wait for its reply |
get_history |
Get message history with a Telegram bot |
Setup
1. Get Telegram API credentials
- Go to https://my.telegram.org/apps
- Log in with your phone number
- Create a new application (any name/description)
- Copy the API ID and API Hash
2. Install and authenticate
# Install
pip install git+https://github.com/tensakulabs/telegram-mcp.git
# Set your credentials
export TELEGRAM_API_ID=12345678
export TELEGRAM_API_HASH=abcdef1234567890abcdef1234567890
export TELEGRAM_PHONE=+15551234567
# Run one-time authentication (sends a code to your Telegram app)
telegram-mcp-auth
3. Configure your MCP client
Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"telegram": {
"command": "uvx",
"args": ["--from", "git+https://github.com/tensakulabs/telegram-mcp.git", "telegram-mcp"],
"env": {
"TELEGRAM_API_ID": "your-api-id",
"TELEGRAM_API_HASH": "your-api-hash",
"TELEGRAM_SESSION_DIR": "/path/to/session/dir"
}
}
}
}
Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"telegram": {
"command": "uvx",
"args": ["--from", "git+https://github.com/tensakulabs/telegram-mcp.git", "telegram-mcp"],
"env": {
"TELEGRAM_API_ID": "your-api-id",
"TELEGRAM_API_HASH": "your-api-hash",
"TELEGRAM_SESSION_DIR": "/path/to/session/dir"
}
}
}
}
Local development
If you've cloned the repo:
{
"mcpServers": {
"telegram": {
"command": "uv",
"args": ["--directory", "/path/to/telegram-mcp", "run", "telegram-mcp"],
"env": {
"TELEGRAM_API_ID": "your-api-id",
"TELEGRAM_API_HASH": "your-api-hash"
}
}
}
}
Configuration
| Environment variable | Required | Default | Description |
|---|---|---|---|
TELEGRAM_API_ID |
Yes | — | Your Telegram API ID |
TELEGRAM_API_HASH |
Yes | — | Your Telegram API hash |
TELEGRAM_PHONE |
Auth only | — | Phone number for authentication |
TELEGRAM_ENV_PATH |
No | Auto-detect | Path to .env file |
TELEGRAM_SESSION_DIR |
No | Working directory | Directory for session file |
How it works
This server uses the Model Context Protocol to expose Telegram interaction as tools that any MCP-compatible AI client can use. Under the hood, it:
- Connects to Telegram via MTProto using your pre-authenticated session
- Sends messages to bots as your user account
- Polls for replies and returns structured JSON responses
- Disconnects cleanly after each operation
Security notes
- Your session file (
telegram_user.session) contains auth tokens — never commit it - The
.gitignoreexcludes session files by default - API credentials should be passed via environment variables, not hardcoded
- This tool acts as YOUR Telegram account — treat it accordingly
Development
git clone https://github.com/tensakulabs/telegram-mcp.git
cd telegram-mcp
uv sync
uv run telegram-mcp
Requirements
- Python 3.10+
- uv (recommended) or pip
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。