MCP-AWS: AI Agent for AWS EC2 Management

@anirban1592

代码仓库

基本信息

分类

云与基础设施

传输方式

stdio

作者

anirban1592

关于 MCP-AWS: AI Agent for AWS EC2 Management

POC : MCP server with openAI agents SDK

MCP-AWS: AI Agent for AWS EC2 Management 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-server-aws-anirban1592": {
      "command": "docker",
      "args": [
        "image",
        "build",
        "-t",
        "my-mcp",
        "."
      ]
    }
  }
}

MCP-AWS: AI Agent for AWS EC2 Management 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-AWS?

MCP-AWS is an AI-driven application that combines OpenAI Agents with a custom MCP server to manage AWS EC2 instances via natural language commands in the terminal. It is designed for developers who want to provision and terminate EC2 instances using conversational instructions.

How to use MCP-AWS?

Install Python 3.12+ (or Docker) and set up an AWS IAM role with EC2 permissions.
Clone the repository and create a .env file with AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION, OPENAI_API_KEY, AMI_ID, INSTANCE_TYPE, KEY_NAME, SECURITY_GROUP_IDS, and AWS_REGION.
Run the app either via Docker (docker image build -t my-mcp then docker container run -it my-mcp) or locally (create a virtual environment with uv, then cd openai-agent/ and uv run agent.py).
At the prompt, enter commands such as “Create an EC2 instance” or “Terminate EC2 instance with ID ”.

Key features of MCP-AWS

Provision EC2 instances using natural language commands
Terminate EC2 instances by providing their instance ID
Integrates OpenAI Agents SDK with a custom MCP server
Supports both Docker and local Python setup
All AWS configuration passed via environment variables

Use cases of MCP-AWS

Quickly spin up an EC2 instance without using the AWS Management Console
Automate the termination of running EC2 instances through conversational prompts
Learn how to build and integrate custom MCP servers with the OpenAI Agents SDK
Prototype natural-language-driven AWS resource management for educational purposes

常见问题

What does MCP-AWS do?

MCP-AWS leverages OpenAI Agents and a custom MCP server to provision and terminate AWS EC2 instances using natural language commands entered in the terminal.

What are the prerequisites for using MCP-AWS?

You need Python 3.12+ or Docker, an AWS IAM role with EC2 permissions, and a `.env` file containing AWS credentials, the OpenAI API key, and EC2 configuration variables (AMI ID, instance type, key name, security group IDs, region).

How do I run MCP-AWS?

You can either build and run the Docker container (`docker image build -t my-mcp` then `docker container run -it my-mcp`) or set up a local Python environment with `uv` and run `uv run agent.py` from the `openai-agent/` directory.

What tools does the MCP server provide?

The MCP server exposes two tools: `initiate_aws_ec2_instance` to create an EC2 instance, and `terminate_aws_ec2_instance` to terminate an instance by its ID.

Is MCP-AWS production-ready?

No. The README states it is a proof of concept intended for learning purposes only. It cautions about IAM role security and AWS billing risks, and disclaims responsibility for any issues that arise.

云与基础设施分类下的更多 MCP 服务器

Lium - GPU cloud

Lium

Find, price and rent GPUs on Lium from Claude, ChatGPT, Codex or any MCP client. Search live GPU availability and prices (H100, H200, B200, RTX 4090 and more), estimate provider earnings, and with Sign in with Lium or a

HostTracker

HostTracker is a website and infrastructure monitoring service that has run external checks since 2004 for more than 500,000 websites. Its official MCP server lets an AI assistant operate a HostTracker account directly i

Terraform MCP Server

hashicorp

The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.

1.5K

Supabase MCP Server

supabase-community

Connect Supabase to your AI assistants

2.8K

Backblaze B2 MCP server

backblaze-labs

MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs