|
At the moment, we’re introducing specialised Mannequin Context Protocol (MCP) servers for Amazon Elastic Container Service (Amazon ECS), Amazon Elastic Kubernetes Service (Amazon EKS), and AWS Serverless, now accessible within the AWS Labs GitHub repository. These open supply options prolong AI growth assistants capabilities with real-time, contextual responses that transcend their pre-trained information. Whereas Giant Language Fashions (LLM) inside AI assistants depend on public documentation, MCP servers ship present context and service-specific steerage that can assist you stop widespread deployment errors and supply extra correct service interactions.
You need to use these open supply options to develop purposes quicker, utilizing up-to-date information of Amazon Internet Providers (AWS) capabilities and configurations through the construct and deployment course of. Whether or not you’re writing code in your built-in growth surroundings (IDE), or debugging manufacturing points, these MCP servers assist AI code assistants with deep understanding of Amazon ECS, Amazon EKS, and AWS Serverless capabilities, accelerating the journey from code to manufacturing. They work with standard AI-enabled IDEs, together with Amazon Q Developer on the command line (CLI), that can assist you construct and deploy purposes utilizing pure language instructions.
- The Amazon ECS MCP Server containerizes and deploys purposes to Amazon ECS inside minutes by configuring all related AWS assets, together with load balancers, networking, auto-scaling, monitoring, Amazon ECS process definitions, and providers. Utilizing pure language directions, you possibly can handle cluster operations, implement auto-scaling methods, and use real-time troubleshooting capabilities to establish and resolve deployment points rapidly.
- For Kubernetes environments, the Amazon EKS MCP Server supplies AI assistants with up-to-date, contextual details about your particular EKS surroundings. It affords entry to the most recent EKS options, information base, and cluster state data. This provides AI code assistants extra correct, tailor-made steerage all through the appliance lifecycle, from preliminary setup to manufacturing deployment.
- The AWS Serverless MCP Server enhances the serverless growth expertise by offering AI coding assistants with complete information of serverless patterns, greatest practices, and AWS providers. Utilizing AWS Serverless Utility Mannequin Command Line Interface (AWS SAM CLI) integration, you possibly can deal with occasions and deploy infrastructure whereas implementing confirmed architectural patterns. This integration streamlines operate lifecycles, service integrations, and operational necessities all through your software growth course of. The server additionally supplies contextual steerage for infrastructure as code selections, AWS Lambda particular greatest practices, and occasion schemas for AWS Lambda occasion supply mappings.
Let’s see it in motion
If that is your first time utilizing AWS MCP servers, go to the Set up and Setup information within the AWS Labs GitHub repository to set up directions. As soon as put in, add the next MCP server configuration to your native setup:
Set up Amazon Q for command line and add the configuration to ~/.aws/amazonq/mcp.json. In the event you’re already an Amazon Q CLI consumer, add solely the configuration.
{
"mcpServers": {
"awslabs.aws-serverless-mcp": {
"command": "uvx",
"timeout": 60,
"args": ["awslabs.aws-serverless_mcp_server@latest"],
},
"awslabs.ecs-mcp-server": {
"disabled": false,
"command": "uv",
"timeout": 60,
"args": ["awslabs.ecs-mcp-server@latest"],
},
"awslabs.eks-mcp-server": {
"disabled": false,
"timeout": 60,
"command": "uv",
"args": ["awslabs.eks-mcp-server@latest"],
}
}
}For this demo I’m going to make use of the Amazon Q CLI to create an software that understands video utilizing 02_using_converse_api.ipynb from Amazon Nova mannequin cookbook repository as pattern code. To do that, I ship the next immediate:
I wish to create a backend software that robotically extracts metadata and understands the content material of pictures and movies uploaded to an S3 bucket and shops that data in a database. I would like to make use of a serverless system for processing. May you generate every little thing I want, together with the code and instructions or steps to arrange the required infrastructure, for it to work from begin to end? - Use 02_using_converse_api.ipynb as instance code for the picture and video understanding.
Amazon Q CLI identifies the required instruments, together with the MCP serverawslabs.aws-serverless-mcp-server. By a single interplay, the AWS Serverless MCP server determines all necessities and greatest practices for constructing a strong structure.
I ask to Amazon Q CLI that construct and take a look at the appliance, however encountered an error. Amazon Q CLI rapidly resolved the difficulty utilizing accessible instruments. I verified success by checking the report created within the Amazon DynamoDB desk and testing the appliance with the dog2.jpeg file.
To boost video processing capabilities, I made a decision emigrate my media evaluation software to a containerized structure. I used this immediate:
I would such as you to create a easy software just like the media evaluation one, however as a substitute of being serverless, it ought to be containerized. Please assist me construct it in a brand new CDK stack.
Amazon Q Developer begins constructing the appliance. I took benefit of this time to seize a espresso. After I returned to my desk, espresso in hand, I used to be pleasantly stunned to seek out the appliance prepared. To make sure every little thing was as much as present requirements, I merely requested:
please evaluation the code and all app utilizing the awslabsecs_mcp_server instruments
Amazon Q Developer CLI provides me a abstract with all of the enhancements and a conclusion.
I ask it to make all the required adjustments, as soon as prepared I ask Amazon Q developer CLI to deploy it in my account, all utilizing pure language.
After a couple of minutes, I evaluation that I’ve an entire containerized software from the S3 bucket to all the required networking.
I ask Amazon Q developer CLI to check the app ship it the-sea.mp4 video file and acquired a timed out error, so Amazon Q CLI decides to make use of the fetch_task_logs from awslabsecs_mcp_server device to evaluation the logs, establish the error after which repair it.
After a brand new deployment, I attempt it once more, and the appliance efficiently processed the video file
I can see the data in my Amazon DynamoDB desk.
To check the Amazon EKS MCP server, I’ve code for an internet app within the auction-website-main folder and I wish to construct an internet sturdy app, for that I requested Amazon Q CLI to assist me with this immediate:
Create an internet software utilizing the present code within the auction-website-main folder. This software will develop, so I wish to create it in a brand new EKS cluster
As soon as the Docker file is created, Amazon Q CLI identifies generate_app_manifests from awslabseks_mcp_server as a dependable device to create a Kubernetes manifests for the appliance.
Then create a brand new EKS cluster utilizing the manage_eks_staks device.
As soon as the app is prepared, the Amazon Q CLI deploys it and offers me a abstract of what it created.
I can see the cluster standing within the console.
After a couple of minutes and resolving a few points utilizing the search_eks_troubleshoot_guide device the appliance is able to use.
Now I’ve a Kitties market internet app, deployed on Amazon EKS utilizing solely pure language instructions by Amazon Q CLI.
Get began at the moment
Go to the AWS Labs GitHub repository to start out utilizing these AWS MCP servers and improve your AI-powered developmen there. The repository consists of implementation guides, instance configurations, and extra specialised servers to run AWS Lambda operate, which transforms your current AWS Lambda features into AI-accessible instruments with out code modifications, and Amazon Bedrock Data Bases Retrieval MCP server, which supplies seamless entry to your Amazon Bedrock information bases. Different AWS specialised servers within the repository embody documentation, instance configurations, and implementation guides to start constructing purposes with better pace and reliability.
To be taught extra about MCP Servers for AWS Serverless and Containers and the way they’ll remodel your AI-assisted software growth, go to the Introducing AWS Serverless MCP Server: AI-powered growth for contemporary purposes, Automating AI-assisted container deployments with the Amazon ECS MCP Server, and Accelerating software growth with the Amazon EKS MCP server deep-dive blogs.
— Eli