MCP Aws: Ai Agent For Aws Ec2 Management

🚀 MCP-AWS: AI Agent for AWS EC2 Management

Welcome to MCP-AWS, a simple yet powerful AI-driven application that combines an OpenAI agent and an MCP server to manage AWS EC2 instances. This application allows you to provision and terminate EC2 instances using natural language commands through the terminal. 🖥️✨

🚀 Quick Start

Prerequisites

1. Python 3.12+ (for local setup) or Docker (for containerized setup)
2. AWS IAM Role: Create an IAM role with permissions to manage EC2 instances.
3. Environment Variables: Prepare a .env file containing the following variables:
   • AWS_ACCESS_KEY_ID
   • AWS_SECRET_ACCESS_KEY
   • AWS_DEFAULT_REGION
   • OPENAI_API_KEY
   • AMI_ID
   • INSTANCE_TYPE
   • KEY_NAME
   • SECURITY_GROUP_IDS
   • AWS_REGION

🏃‍♂️ Running the Application

1. Clone the repository:

   git clone https://github.com/anirban1592/mcp-server-aws.git
   cd mcp-aws
   

2. Create a .env file as described in the prerequisites.

Option 1: Docker Setup (Recommended)

3. Build the Docker image:

   docker image build -t my-mcp .
   

4. Run the container:

   docker container run -it my-mcp
   

Option 2: Local Setup

3. Create and activate a virtual environment:

   pip install uv
   uv venv .venv
   # Windows
   .venv\Scripts\activate
   # Unix/MacOS
   source .venv/bin/activate
   

4. Run the application:

   cd openai-agent/
   uv run agent.py
   

💬 Using the AI Agent

1. Provision an EC2 instance:

   Enter your command: Provision an EC2 instance
   

2. Terminate an EC2 instance:

   Enter your command: Terminate the EC2 instance with instance ID <instance-id>
   

🎥 Demo Video

Watch the demo video to see MCP-AWS in action! 🚀

✨ Features

1. Provision EC2 Instances: Simply tell the AI agent to create an EC2 instance, and it will handle everything for you and provide the instance ID. 🛠️
2. Terminate EC2 Instances: Provide the instance ID, and the agent will terminate the instance for you. ❌
3. MCP Server Integration: Explore how to create and integrate a custom MCP server with the OpenAI Agent SDK. 🧩

🛠️ Tools in the MCP Server

The MCP server is a custom server that includes two tools:

1. initiate_aws_ec2_instance: Create an AWS EC2 instance.
2. terminate_aws_ec2_instance: Terminate an AWS EC2 instance by its instance ID.

⚠️ Important Note

• IAM Roles and Credentials: Use AWS IAM roles and credentials at your own risk. Ensure you follow AWS security best practices.
• Billing and Security: This application is for learning purposes only. We are not responsible for any billing issues or security incidents.

📚 Documentation

This project demonstrates:

1. How to integrate an MCP server with the OpenAI Agent SDK
2. How to build a simple AI-driven application for AWS resource management

Enjoy exploring the power of AI and the MCP server! 🌟