Telegram Notify MCP Server
Connects VS Code Copilot to Telegram for mobile notifications, interactive approval workflows, and remote command input. Enables users to monitor AI agents, approve sensitive operations, and provide follow-up instructions from their smartphone.
README
mcp-telegram-notify
A Model Context Protocol (MCP) server that bridges VS Code Copilot with Telegram, enabling mobile notifications, approval workflows, and remote prompt input from your smartphone.
Features
- Notifications — Send task completion reports to Telegram
- Approval Flow — Inline keyboard buttons for approve/reject decisions
- Remote Prompt — Receive next instructions from your phone via free-text response
- File Sharing — Send files (logs, JSON results) directly to Telegram
Use Case: Copilot Autopilot + Mobile Control
VS Code Copilot (Autopilot mode, auto-approve ON)
→ Executes tasks automatically
→ Asks approval via Telegram before destructive ops
→ Reports completion to your phone
→ Waits for your next instruction via Telegram
→ Continues working
No need to be at your desk — control Copilot entirely from your smartphone.
Installation
pip install mcp-telegram-notify
Or install from source:
git clone https://github.com/NobufumiMurata/mcp-telegram-notify.git
cd mcp-telegram-notify
pip install -e ".[dev]"
Setup
1. Create a Telegram Bot
- Open Telegram and message @BotFather
- Send
/newbotand follow the prompts - Copy the bot token
2. Get Your Chat ID and User ID
Send any message to your bot, then:
curl "https://api.telegram.org/bot<YOUR_TOKEN>/getUpdates"
From the response, note:
"chat": {"id": ...}→ your Chat ID"from": {"id": ...}→ your User ID (for the allowlist)
3. Configure VS Code MCP
Add to your .vscode/mcp.json:
{
"servers": {
"telegram-notify": {
"command": "python",
"args": ["-m", "mcp_telegram_notify"],
"env": {
"TELEGRAM_BOT_TOKEN": "<your-bot-token>",
"TELEGRAM_CHAT_ID": "<your-chat-id>",
"TELEGRAM_ALLOWED_USERS": "<your-user-id>"
}
}
}
}
Alternative: JSON Config File
Instead of environment variables, you can use a JSON config file:
{
"bot_token": "<your-bot-token>",
"chat_id": "<your-chat-id>",
"allowed_users": ["<your-user-id>"]
}
Then set TELEGRAM_CONFIG_PATH to point to the file:
{
"servers": {
"telegram-notify": {
"command": "python",
"args": ["-m", "mcp_telegram_notify"],
"env": {
"TELEGRAM_CONFIG_PATH": "secrets/telegram-bot.json"
}
}
}
}
MCP Tools
| Tool | Description | Key Args |
|---|---|---|
telegram_notify |
Send a text message (HTML) | message |
telegram_ask_approval |
Inline buttons + wait for selection | question, options, timeout_minutes |
telegram_wait_response |
Send prompt + wait for free-text reply | prompt, timeout_minutes |
telegram_send_file |
Send a file | file_path, caption |
Example: Copilot Agent Instructions
Add to your .github/agents/*.agent.md to make Copilot use these tools automatically:
## Notification Rules (Telegram MCP)
- Before destructive operations (VM stop/delete, resource deletion, network changes),
use telegram_ask_approval to get explicit user approval
- After completing a task, use telegram_notify to send a summary report
- After sending the report, use telegram_wait_response to receive the next instruction
- Treat the received instruction as a new task and continue processing
Security
- User allowlist: Only messages from
TELEGRAM_ALLOWED_USERSare accepted. All other users are silently ignored. - Timeouts: All waiting operations have configurable timeouts (default: 5 min for approval, 10 min for text). Returns
TIMEOUTstatus on expiry. - No secrets in repo: All credentials via environment variables or external config file.
- Stale update draining: Old Telegram updates are consumed before waiting, preventing stale responses from being accepted.
Development
git clone https://github.com/NobufumiMurata/mcp-telegram-notify.git
cd mcp-telegram-notify
pip install -e ".[dev]"
pytest
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。