广告合作
MCP.so
登录

MCP Integration example with Telegram

@arananet

代码仓库

基本信息

分类

沟通协作

许可证

MIT license

传输方式

stdio

作者

arananet

关于 MCP Integration example with Telegram

A Python-based Model Context Protocol (MCP) client and server that enables LLMs to send notifications via Telegram and receive user responses.

MCP Integration example with Telegram 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-telegram-poc": {
      "command": "python3",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

MCP Integration example with Telegram 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Integration example with Telegram?

A Python-based Model Context Protocol (MCP) client and server that enables LLMs to send notifications via Telegram and receive user responses. It decouples the LLM’s reasoning from the execution of external actions, making tool integration more modular and maintainable.

How to use MCP Integration example with Telegram?

Clone the repository, install dependencies (pip install -r requirements.txt), create a virtual environment, and fill in your Telegram credentials in a .env file (Telegram bot token, chat ID, OpenAI API key). Run the server with python3 src/mcp_handler.py, or test client interaction with python3 examples/test_client.py. The server exposes two tools: send_alert (sends a Telegram message) and check_reply (polls for replies).

Key features of MCP Integration example with Telegram

  • Send text alerts to Telegram with customizable urgency levels
  • Check for user replies with configurable timeouts
  • Integration with MCP‑compatible LLM applications
  • Decouples reasoning from execution for safer tool use
  • Update external tools without changing LLM prompts
  • Supports AutoGen 0.4 framework integration

Use cases of MCP Integration example with Telegram

  • Notify a user of critical events and wait for confirmation
  • Enable an LLM to send alerts and process human feedback
  • Prototype MCP‑based tool integrations with messaging platforms
  • Demonstrate modular architecture for LLM‑driven workflows

常见问题

1

How does MCP differ from function calls or agent tools?

MCP separates the LLM’s decision‑making from execution; you can swap out tools without modifying the LLM. Direct function calls or agent methods mix logic, making maintenance harder.

2

What are the prerequisites?

Python 3.11+, a Telegram bot token (from @BotFather), your Telegram chat ID, and an OpenAI API key.

3

How do I get a Telegram bot token and find my chat ID?

Chat with @BotFather on Telegram, send `/newbot`, and follow the prompts. To find your chat ID, send a message to your bot, then visit `https://api.telegram.org/bot<YOUR_BOT_TOKEN>/getUpdates` and look for the `chat` object’s `id` field.

4

What runtime environment is needed?

The server runs as a standalone Python script. Use a virtual environment and install dependencies from `requirements.txt`. It is tested on Linux/macOS.

5

Are there known limits?

The README does not specify limits beyond the configurable `timeout_seconds` for `check_reply` (default 60 seconds). The server uses polling for replies.

评论

沟通协作 分类下的更多 MCP 服务器

Caulo

Patry

Caulo is the social layer of the agentic web: a social network your AI agent reads, briefs you on, and posts to — by prompt. Ad-free, verified humans only, with provenance on every post (human / agent-assisted / agent-au

Mobile Text Alerts SMS

Mobile Text Alerts

Official Mobile Text Alerts server. Send and schedule SMS, manage subscribers and groups, and complete carrier registration from any MCP-compatible AI assistant.

B2B Creators

Social Tree Global

Agencies and GTM teams use HeyReach and Instantly to run LinkedIn outbound from personal sender profiles — but those profiles sit empty and prospects don't accept. B2B Creators is the content layer that keeps every sende

Pidgeon

Pidgeon

Email inboxes for AI agents. Give an agent its own address in one call; it sends, receives and replies in threads, waits for a sign-up code and gets it back already extracted, and hands a conversation to a person when it

call4me

Nick Khami

call4me lets your AI agent make real phone calls for you. Ask Claude, ChatGPT, Cursor, Codex or your own app to book a table, schedule a dentist appointment, cancel a subscription or ask a business a question. It calls,

广告合作