返回 MCP 目录
public公开cloud托管运行

腾讯云自动化助手TAT MCP Server

腾讯云 TAT(TencentCloud Automation Tools)MCP Server,用于在支持 MCP 的客户端中直接在腾讯云实例上执行命令。

article

README

Tencent Cloud TAT MCP Server

An MCP server implementation for executing commands on Tencent Cloud instances using the TencentCloud Automation Tools (TAT) API.

Features

  • Command Execution: Execute Shell/PowerShell commands on Tencent Cloud instances
  • Sync & Async Support: Both synchronous and asynchronous command execution
  • Cross-Platform: Supports both Linux and Windows instances
  • Task Management: Query command execution results and outputs

API List

🚀 Command Execution

| Tool Name | Description | |---|---| | SyncRunCommand | Synchronously execute commands on instances | | RunCommand | Asynchronously execute commands on instances |

📊 Task Management

| Tool Name | Description | |---|---| | QueryTask | Retrieve command execution results |

Configuration

Setting up Tencent Cloud Credentials

  1. Obtain SecretId and SecretKey from Tencent Cloud Console
  2. Set your default region (optional)

Environment Variables

Configure the following environment variables:

  • TENCENTCLOUD_SECRET_ID: Tencent Cloud SecretId
  • TENCENTCLOUD_SECRET_KEY: Tencent Cloud SecretKey
  • TENCENTCLOUD_REGION: Default region (optional)

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "tencent-tat": {
      "command": "uv",
      "args": ["run", "mcp-server-tat"],
      "env": {
        "TENCENTCLOUD_SECRET_ID": "YOUR_SECRET_ID_HERE",
        "TENCENTCLOUD_SECRET_KEY": "YOUR_SECRET_KEY_HERE",
        "TENCENTCLOUD_REGION": "YOUR_REGION_HERE"
      }
    }
  }
}

Installation

pip install mcp-server-tat

License

MIT License. See LICENSE for details.

help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端