Advertise
MCP.so
Sign In

MCP-AWS: AI Agent for AWS EC2 Management

@anirban1592

Repository

Basic information

Category

Cloud & Infrastructure

Transports

stdio

Author

anirban1592

About MCP-AWS: AI Agent for AWS EC2 Management

POC : MCP server with openAI agents SDK

MCP-AWS: AI Agent for AWS EC2 Management config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-aws-anirban1592": {
      "command": "docker",
      "args": [
        "image",
        "build",
        "-t",
        "my-mcp",
        "."
      ]
    }
  }
}

MCP-AWS: AI Agent for AWS EC2 Management tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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?

  1. Install Python 3.12+ (or Docker) and set up an AWS IAM role with EC2 permissions.
  2. 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.
  3. 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).
  4. 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

Frequently asked questions

1

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.

2

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).

3

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.

4

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.

5

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.

Comments

More Cloud & Infrastructure MCP servers

Dockhold

dockhold

Put the project you are working on online. Deploys the current folder or a GitHub repo to a live HTTPS URL on Dockhold; reads status and logs, sets variables, resizes apps and databases...

Query | MCP server for Supabase

alexander-zuev

Query MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.

828

Aws Kb Retrieval Server

modelcontextprotocol

Model Context Protocol Servers

88.2K

Mcp K8s Go

strowk

MCP server connecting to Kubernetes

383

Tessryx

Build and run websites, APIs, automations, and admin tools from chat. Your agent creates the data, logic, pages, and scheduled jobs; Tessryx hosts them on your own domain. No code generated, nothing to deploy.

Advertise