这是一个Telegram的模型上下文协议（MCP）服务器。

通过这个功能，你可以搜索个人的Telegram消息，搜索联系人，并向个人或群组发送消息。

它通过Telegram API（使用Telethon库）直接连接到你的个人Telegram账户。你所有的消息都存储在本地的SQLite数据库中，只有当代理通过你控制的工具访问时才会发送给大型语言模型（比如Claude）。

安装

先决条件

• Python 3.6+
• Anthropic Claude桌面应用（或光标）

步伐

1. 克隆此仓库

创建一个Python虚拟环境并激活它：

安装依赖：

该环境既可用于运行Telegram桥接也可用于MCP服务器。

2. 获取你的Telegram API凭证

• 前往https://my.telegram.org/auth
• 登录并进入“API 开发工具”
• 创建一个新应用
• 记录你的API ID和API哈希

3. 运行电报桥接

导航到telegram-bridge目录：

将你的API凭据设置为环境变量，可以通过导出它们：

或者通过创建一个“。

Telegram MCP Server

This is a Model Context Protocol (MCP) server for Telegram.

With this you can search your personal Telegram messages, search your contacts, and send messages to either individuals or groups.

It connects to your personal Telegram account directly via the Telegram API (using the Telethon library). All your messages are stored locally in a SQLite database and only sent to an LLM (such as Claude) when the agent accesses them through tools (which you control).

Installation

Prerequisites

• Python 3.6+
• Anthropic Claude Desktop app (or Cursor)

Steps

1. Clone this repository

   git clone https://github.com/Muhammad18557/telegram-mcp.git
   cd telegram-mcp
   

   Create a Python virtual environment and activate it:

   python3 -m venv myenv
   source myenv/bin/activate
   

   Install dependencies:

   pip install -r requirements.txt
   

   This is the environment that can be used both for running the Telegram bridge and the MCP server.

2. Get your Telegram API credentials

   • Go to https://my.telegram.org/auth
   • Log in and go to “API development tools”
   • Create a new application
   • Note your API ID and API hash

3. Run the Telegram bridge

   Navigate to the telegram-bridge directory:

   cd telegram-bridge
   

   Set up your API credentials as environment variables either by exporting them:

   export TELEGRAM_API_ID=your_api_id
   export TELEGRAM_API_HASH=your_api_hash
   

   Or by creating a .env file based on the provided .env.example:

   cp .env.example .env
   nano .env  # or use your preferred text editor
   

   Then update the values in the .env file:

   TELEGRAM_API_ID=your_api_id
   TELEGRAM_API_HASH=your_api_hash
   

   Run the Python application:

   python main.py
   

   The first time you run it, you will be prompted to enter your phone number and the verification code sent to your Telegram account.

4. Connect to the MCP server

   First, update the run_telegram_server.sh script with your absolute repository path:

   # Open the script in your preferred editor
   nano run_telegram_server.sh
   
   # Update line 4 with your absolute path to the repository
   # Change this:
   BASE_DIR="/Users/muhammadabdullah/Desktop/mcp/telegram-mcp"
   # To your actual BASE_DIR path (get it by running `pwd` in the telegram-mcp directory)
   

   Then, configure the MCP server by creating a JSON configuration file with the following format. Use the BASE_DIR from above.

   {
     "mcpServers": {
       "telegram": {
         "command": "/bin/bash",
         "args": [
           "{{BASE_DIR}}/run_telegram_server.sh"
         ]
       }
     }
   }