DEV Community

AWS Community Builders profile image xbill
xbill for AWS Community Builders

Posted on • Originally published at xbill999.Medium on

MCP Development with Amazon Elastic Beanstalk (EBS)

#agents #elasticbeanstalk #mcps #gemini

Leveraging Gemini CLI and the underlying Gemini LLM to build Model Context Protocol (MCP) AI applications with Python from a local development environment deployed to the EBS service on AWS.

Yet another Python MCP Demo?

Yes — thanks for asking.

Python has traditionally been the main coding language for ML and AI tools. The goal of this article is to provide a minimal viable basic working MCP stdio server that can be run locally without any unneeded extra code or extensions.

What Is Python?

Python is an interpreted language that allows for rapid development and testing and has deep libraries for working with ML and AI:

Welcome to Python.org

Python Version Management

One of the downsides of the wide deployment of Python has been managing the language versions across platforms and maintaining a supported version.

The pyenv tool enables deploying consistent versions of Python:

GitHub - pyenv/pyenv: Simple Python version management

As of writing — the mainstream python version is 3.13. To validate your current Python:

admin@ip-172-31-70-211:~/gemini-cli-aws/mcp-lightsail-python-aws$ python --version
Python 3.13.12
Enter fullscreen mode Exit fullscreen mode

Gemini CLI

If not pre-installed you can download the Gemini CLI to interact with the source files and provide real-time assistance:

npm install -g @google/gemini-cli
Enter fullscreen mode Exit fullscreen mode

Testing the Gemini CLI Environment

Once you have all the tools and the correct Node.js version in place- you can test the startup of Gemini CLI. You will need to authenticate with a Key or your Google Account:

xbill@penguin:~$ gemini

 ▝▜▄ Gemini CLI v0.40.1
   ▝▜▄
  ▗▟▀ Signed in with Google /auth
 ▝▀ Plan: Gemini Code Assist Standard /upgrade
Enter fullscreen mode Exit fullscreen mode

Node Version Management

Gemini CLI needs a consistent, up to date version of Node. The nvm command can be used to get a standard Node environment:

GitHub - nvm-sh/nvm: Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

Python MCP Documentation

The official GitHub Repo provides samples and documentation for getting started:

GitHub - modelcontextprotocol/python-sdk: The official Python SDK for Model Context Protocol servers and clients

The most common MCP Python deployment path uses the FASTMCP library:

Welcome to FastMCP - FastMCP

Docker Version Management

The AWS Cli tools and Lightsail extensions need current version of Docker. If your environment does not provide a recent docker tool- the Docker Version Manager can be used to downlaod the latest supported Docker:

Install

Amazon Elastic Bean Stalk

AWS Elastic Beanstalk is a Platform-as-a-Service (PaaS) used for deploying and scaling web applications and services into the Amazon Web Services (AWS) Cloud. [1, 2]

It simplifies the development process by allowing you to upload your application code while the service automatically manages the complex infrastructure details.

More details are here:

Web App Deployment - AWS Elastic Beanstalk - AWS

The EBS console looks similar to this:

AWS CLI

The AWS CLI provides a command line tool to directly access AWS services from your current environment. Full details on the CLI are available here:

Install Docker, AWS CLI, and the Lightsail Control plugin for containers

Where do I start?

The strategy for starting MCP development is a incremental step by step approach.

First, the basic development environment is setup with the required system variables, and a working Gemini CLI configuration.

Then, a minimal Hello World Style Python MCP Server is built with HTTP transport. This server is validated with Gemini CLI in the local environment.

This setup validates the connection from Gemini CLI to the local process via MCP. The MCP client (Gemini CLI) and the Python MCP server both run in the same local environment.

Next- the MCP server is wrapped in a container with docker and deployed to Amazon Elastic Beanstalk. This remote deployment is validated with Gemini CLI running as a MCP client.

Setup the Basic Environment

At this point you should have a working Python interpreter and a working Gemini CLI installation. The next step is to clone the GitHub samples repository with support scripts:

cd ~
git clone https://github.com/xbill9/gemini-cli-aws
Enter fullscreen mode Exit fullscreen mode

Then run init.sh from the cloned directory.

The script will attempt to determine your shell environment and set the correct variables:

cd gemini-cli-aws
source init.sh
Enter fullscreen mode Exit fullscreen mode

If your session times out or you need to re-authenticate- you can run the set_env.sh script to reset your environment variables:

cd gemini-cli-aws
source set_env.sh
Enter fullscreen mode Exit fullscreen mode

Variables like PROJECT_ID need to be setup for use in the various build scripts- so the set_env script can be used to reset the environment if you time-out.

Hello World with HTTP Transport

One of the key features that the standard MCP libraries provide is abstracting various transport methods.

The high level MCP tool implementation is the same no matter what low level transport channel/method that the MCP Client uses to connect to a MCP Server.

The simplest transport that the SDK supports is the stdio (stdio/stdout) transport — which connects a locally running process. Both the MCP client and MCP Server must be running in the same environment.

The HTTP transport allows the MCP client and server to run in the same environment or distributed over the Internet.

The connection over HTTP will look similar to this:

mcp.run(
        transport="http",
        host="0.0.0.0",
        port=port,
    )
Enter fullscreen mode Exit fullscreen mode

Running the Python Code

First- switch the directory with the Python MCP sample code:

cd ~/gemini-cli-aws/mcp-ebs-python-aws
Enter fullscreen mode Exit fullscreen mode

Refresh the AWS credentials:

xbill@penguin:~/gemini-cli-aws/mcp-ebs-python-aws$ aws login --remote

xbill@penguin:~/gemini-cli-aws/mcp-ebs-python-aws$ source save-aws-creds.sh 
Exporting AWS credentials...
Successfully saved credentials to .aws_creds
The Makefile will now automatically use these for deployments.
Enter fullscreen mode Exit fullscreen mode

Run the deploy version on the local system:

xbill@penguin:~/gemini-cli-aws/mcp-ebs-python-aws$ make deploy
Creating Lightsail instance mcp-vps-python-aws...
Instance already exists or creation in progress.
Waiting for instance mcp-vps-python-aws to reach 'running' state...
Instance is running.
Enter fullscreen mode Exit fullscreen mode

You can validate the final result by checking the messages:

  Environment Status: mcp-server-eb-env
   * Status: Ready
   * Health: Green
   * Platform: Docker running on 64bit Amazon Linux 2/4.8.2
   * Deployed Version: app-260508_165941877951
   * CNAME: mcp-server-eb-env.eba-ce3smmqd.us-east-1.elasticbeanstalk.com

  Recent Events
  The environment was recently created and updated successfully:
   * 20:56:10: createEnvironment started.
   * 20:59:32: Initial instance deployment completed.
   * 20:59:38: Successfully launched environment.
   * 21:00:03: Subsequent instance deployment completed successfully.
Enter fullscreen mode Exit fullscreen mode

You can then get the endpoint:

 > make endpoint

  Retrieving Application Endpoint: Retrieving the public endpoint URL of the Elastic Beanstalk environment.

╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ Shell make endpoint │
│ │
│ http://mcp-server-eb-env.eba-ce3smmqd.us-east-1.elasticbeanstalk.com │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

✦ The public endpoint for your Elastic Beanstalk environment is:

  http://mcp-server-eb-env.eba-ce3smmqd.us-east-1.elasticbeanstalk.com
Enter fullscreen mode Exit fullscreen mode

The service will be visible in the AWS console:

Gemini CLI settings.json

Once you have the deployed endpoint — update the Gemini CLI MCP settings:

{
  "mcpServers": {
    "mcp-ebs-python-aws": {
      "httpUrl": "http://mcp-server-eb-env.eba-ce3smmqd.us-east-1.elasticbeanstalk.com/mcp/"
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Remote MCP Server Testing

Restart Gemini CLI and check for the new MCP tools:

xbill@penguin:~/gemini-cli-aws/mcp-ebs-python-aws$ gemini

 ▝▜▄ Gemini CLI v0.41.2
   ▝▜▄
  ▗▟▀ Signed in with Google /auth
 ▝▀ Plan: Gemini Code Assist Standard /upgrade

🟢 mcp-ebs-python-aws - Ready (1 tool)
  Tools:
  - mcp_mcp-ebs-python-aws_greet
Enter fullscreen mode Exit fullscreen mode

Then the remote MCP tool in EBS can be called:

 > mcp_mcp-ebs-python-aws_greet Hello Beanstalk!

  Topic: Executing the greet tool to verify the MCP server functionality.

╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ greet (mcp-ebs-python-aws MCP Server) {"param":"Hello Beanstalk!"} │
│ │
│ Hello, Hello Beanstalk!! │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

✦ Hello, Hello Beanstalk!!
Enter fullscreen mode Exit fullscreen mode

Gemini CLI can also summarize the deployment:

> summarize the deployment

✦ The mcp-ebs-python-aws project is a Python-based Model Context Protocol (MCP) server deployed to AWS Elastic Beanstalk (EB) using Docker.

  Deployment Architecture
   * Server Framework: Built with FastMCP and Starlette, providing an asynchronous foundation for MCP tools and standard HTTP endpoints.
   * Infrastructure: Uses the Elastic Beanstalk Docker platform, which automatically handles capacity provisioning, load balancing, and
     auto-scaling.
   * Compute: Defaults to t3.micro instances in the us-east-1 region.

  Deployment Workflow (make deploy)
  The deployment is automated via a Makefile and deploy.sh script:
   1. Validation: Runs unit tests using pytest to ensure code quality before deployment.
   2. Initialization: Uses the EB CLI (eb init) to configure the project for the AWS Docker platform.
   3. Provisioning: Creates the environment (eb create) if it doesn't exist, setting up the required AWS resources (ALB, ASG, EC2).
   4. Updates: Deploys code changes (eb deploy), which triggers a Docker build and rolling update on the EB instances.

  Key Endpoints
  Once deployed, the environment provides:
   * MCP SSE Transport: http://<eb-cname>/mcp
   * Health Check: http://<eb-cname>/health (used by EB for monitoring)
   * Root Info: http://<eb-cname>/

  Management Commands
   * make status: Displays the current health of the EB environment and recent deployment events.
   * make endpoint: Retrieves the public URL of the deployed server.
   * make aws-destroy: Terminates the environment and all associated AWS resources to stop billing.
Enter fullscreen mode Exit fullscreen mode

Summary

The strategy for using Python for MCP development with Gemini CLI on Amazon EBS was validated with a incremental step by step approach.

This MCP server was then deployed to Amazon Elastic Bean Stalk. The local copy of Gemini CLI was used as a MCP client to validate the connection.

This approach can be extended to more complex deployments using other MCP transports and Cloud based options.

Top comments (0)