The rmcp crate and standard Rust libraries are used to build a basic MCP Server in Rust. This MCP Server is then built and deployed to AWS Elastic Bean Stalk and validated locally with Gemini CLI
More MCP Demos?
Yes sir. Ferris the Crab would have nothing less.
Why not just use Python?
Python has traditionally been the main coding language for ML and AI tools. One of the strengths of the MCP protocol is that the actual implementation details are independent of the development language. The reality is that not every project is coded in Python- and MCP allows you to use the latest AI appt roaches with other coding languages.
What is this Tutorial Trying to Do?
Building on previous tutorials, the goal is to extend a Rust MCP server with basic support for deployment to AWS.
What is Rust?
Rust is a high performance, memory safe, compiled language:
Rust provides memory safe operations beyond C/C++ and also can provide exceptional performance gains as it is compiled directly to native binaries.
So is this the real Slim Shady?
So what is different about this lab compared to all the others out there?
This is one of the first deep dives into deploying a Rust based MCP server hosted on AWS. The Amazon Elastic Bean Stalk service was targeted for ease of setup and deployment.
Rust Setup
Instructions to install Rust are available here:
For a Linux like environment the command looks like this:
curl — proto ‘=https’ — tlsv1.2 -sSf https://sh.rustup.rs | sh
Rust also depends on a working C compiler and OpenSSL setup. For a Debian 12 system — install the basic tools for development:
sudo apt install build-essential
sudo apt install libssl-dev
sudo apt install pkg-config
sudo apt-get install libudev-dev
sudo apt install make
sudo apt install git
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
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:
▝▜▄ Gemini CLI v0.33.1
▝▜▄
▗▟▀ Logged in with Google /auth
▝▀ Gemini Code Assist Standard /upgrade no sandbox (see /docs) /model Auto (Gemini 3) | 239.8 MB
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
You can version check the tool after installation:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ aws --version
aws-cli/2.34.43 Python/3.14.4 Linux/6.6.99-09128-g14e87a8a9b71 exe/x86_64.debian.12
Amazone Elastic Bean Stalk
AWS Elastic Beanstalk is an orchestration service from Amazon Web Services (AWS) that simplifies the process of deploying and scaling web applications. It is a Platform-as-a-Service (PaaS) that abstracts the underlying infrastructure, allowing developers to focus on writing code while AWS automatically handles resource provisioning, load balancing, auto-scaling, and health monitoring. [1, 2, 3]
More information is available on the official site here:
Web App Deployment - AWS Elastic Beanstalk - AWS
Setup the Basic Environment
At this point you should have a working Rust environment and a working Gemini CLI installation. All of the relevant code examples and documentation is available in GitHub.
The next step is to clone the GitHub repository to your local environment:
cd ~
git clone https://github.com/xbill9/gemini-cli-aws
Then run init.sh from the cloned directory.
The script will attempt to determine your shell environment and set the correct variables:
source init.sh
If your session times out or you need to re-authenticate- you can run the set_env.sh script to reset your environment variables:
source set_env.sh
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.
Refresh the AWS credentials:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ aws login --remote
Browser will not be automatically opened.
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ source save-aws-creds.sh
Exporting AWS credentials...
Successfully saved credentials to .aws_creds
The Makefile will now automatically use these for deployments.
Finally install the packages and dependencies:
~/gemini-cli-aws/mcp-ebs-rust-aws
Build The Rust MCP Server
Some background information on building and configuring a Rust MCP server is here:
Building a Secure HTTP Transport MCP Server with Rust, and Gemini CLI
The mcp-mcp-rust subdirectory has the complete Rust MCP server in one subdirectory.
Minimal System Information Tool Build
The first step is to build the basic tool directly with Rust. This allows the tool to be debugged and tested locally before adding the MCP layer.
First build the tool locally:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make
Building the Rust project...
Compiling mcp-ebs-rust-aws v1.0.0 (/home/xbill/gemini-cli-aws/mcp-ebs-rust-aws)
Finished `dev` profile [unoptimized + debuginfo] target(s) in 14.90s
then lint check the code:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make lint
Linting code...
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.48s
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$
and run local tests:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make test
Running tests...
Finished `test` profile [unoptimized + debuginfo] target(s) in 0.87s
Running unittests src/main.rs (target/debug/deps/mcp_ebs_rust_aws-7697fb144684b313)
running 1 test
test tests::test_greeting ... ok
test result: ok. 1 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$
The last step is to build the production version:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make release
Building Release...
Finished `release` profile [optimized] target(s) in 0.30s
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$
The MCP server can be started locally:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make start
Building Release...
Finished `release` profile [optimized] target(s) in 0.08s
Starting the MCP server...
Server started with PID 8284
Then Gemini CLI is used as a MCP client:
/mcp list
🟢 local-rust - Ready (1 tool)
Tools:
- mcp_local-rust_greeting
The MCP tool can then be tested:
> mcp_local-rust_greeting hello local!
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Action Required │
│ │
│ ? greeting (local-rust MCP Server) {"message":"hello local!"} │
│ │
│ MCP Server: local-rust │
│ Tool: greeting │
│ │
│ MCP Tool Details: │
│ (press Ctrl+O to expand MCP tool details) │
│ Allow execution of MCP tool "greeting" from server "local-rust"? │
│ │
│ 1. Allow once │
│ 2. Allow tool for this session │
│ ● 3. Allow all server tools for this session │
│ 4. Allow tool for all future sessions ~/.gemini/policies/auto-saved.toml │
│ 5. No, suggest changes (esc) │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ greeting (local-rust MCP Server) {"message":"hello local!"} │
│ │
│ Hello World MCP! hello local! │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ Hello World MCP! hello local!
Deploy To Elastic Bean Stalk
A basic Dockerfile is used to build an image for deployment:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make deploy
Building Release...
Finished `release` profile [optimized] target(s) in 0.20s
Creating dist bundle (dist.zip)...
adding: Dockerfile (deflated 26%)
adding: mcp-ebs-rust-aws (deflated 57%)
Deploying dist.zip to Elastic Beanstalk... 0.0s
Get the Endpoint:
xbill@penguin:~/gemini-cli-aws/mcp-ebs-rust-aws$ make endpoint
Elastic Beanstalk public endpoint:
mcp-ebs-rust-aws-env-v2.eba-gxgrdggn.us-east-1.elasticbeanstalk.com
Check Gemini MCP settings:
{
"mcpServers": {
"aws-ebs-rust": {
"httpUrl": "http://mcp-ebs-rust-aws-env-v2.eba-gxgrdggn.us-east-1.elasticbeanstalk.com/mcp"
},
"local-rust": {
"httpUrl": "http://127.0.0.1:8080/mcp"
}
}
}
The service will be visible on the AWS console:
Final Test
Start up Gemini CLI and check the MCP server status:
> /mcp list
Configured MCP servers:
🟢 aws-ebs-rust - Ready (1 tool)
Tools:
- mcp_aws-ebs-rust_greeting
Then run the remote MCP tool:
> mcp_aws-ebs-rust_greeting Hello Stalk of Beans
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Action Required │
│ │
│ ? greeting (aws-ebs-rust MCP Server) {"message":"Hello Stalk of Beans"} │
│ │
│ MCP Server: aws-ebs-rust │
│ Tool: greeting │
│ │
│ MCP Tool Details: │
│ (press Ctrl+O to expand MCP tool details) │
│ Allow execution of MCP tool "greeting" from server "aws-ebs-rust"? │
│ │
│ 1. Allow once │
│ 2. Allow tool for this session │
│ 3. Allow all server tools for this session │
│ ● 4. Allow tool for all future sessions ~/.gemini/policies/auto-saved.toml │
│ 5. No, suggest changes (esc) │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ greeting (aws-ebs-rust MCP Server) {"message":"Hello Stalk of Beans"} │
│ │
│ Hello World MCP! Hello Stalk of Beans │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ Hello World MCP! Hello Stalk of Beans
Summary
A complete HTTP transport MCP server was built using Rust. This application was tested locally with Gemini CLI. Then, the entire solution was deployed to AWS Elastic Bean Stalk. The remote MCP server was validated with Gemini CLI locally.


Top comments (0)