awslabs.eks-mcp-server

What it is and what it does

This package is an MCP (Model Context Protocol) server that bridges AI code assistants to Amazon EKS clusters. It translates natural language requests from LLMs into AWS and Kubernetes API calls, enabling AI assistants to perform cluster operations without requiring users to write infrastructure code directly.

The server supports the full lifecycle of EKS management: creating new clusters with VPCs and networking via CloudFormation, deploying containerized applications from YAML or generated manifests, managing individual Kubernetes resources (create, read, update, patch, delete), listing and filtering resources by namespace or labels, retrieving pod logs and events, and troubleshooting cluster issues. It requires Python 3.10+, AWS credentials, and appropriate IAM permissions; Kubernetes API access is controlled by either IAM access entries or kubeconfig credentials depending on your authentication mode.

Use it for:

• Provision new EKS clusters with prerequisites (VPCs, subnets, networking) by translating natural language into CloudFormation templates.
• Deploy containerized applications to existing EKS clusters by applying user-provided Kubernetes YAML or generated manifests.
• Perform full lifecycle operations on Kubernetes resources through natural language queries in your IDE's AI assistant.
• Retrieve pod logs and Kubernetes events for troubleshooting and monitoring without leaving your code editor.
• Streamline cluster setup by having an AI assistant apply best practices and handle prerequisite creation automatically.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Connects AI code assistants to Amazon EKS clusters via the Model Context Protocol, enabling LLMs to create clusters, deploy applications, manage Kubernetes resources, and troubleshoot issues through natural language.

Yes, if you use Cursor, Kiro, or VS Code with AI assistants and need to manage EKS clusters from within your IDE. The package is actively maintained, has no known vulnerabilities, and low install friction. Requires careful IAM permission management in production—read-only mode is safe for exploration, but write operations demand restrictive policies and trusted environments. Not applicable if you don't use an MCP-compatible AI assistant.

Install

awslabs-eks-mcp-server on PyPI

pip install awslabs-eks-mcp-server

uv add awslabs-eks-mcp-server

poetry add awslabs-eks-mcp-server

Installing awslabs.eks-mcp-server

Before you install

Low friction install with a pure-Python wheel. Active maintenance (last commit 2026-08-14, released 2026-08-10) and strong community signal (9598 repository stars). Requires Python 3.10+ and AWS CLI credentials configured; no compiled dependencies.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions. You may use, modify, and distribute this package freely provided you include the license notice.

Quickstart

pip install awslabs.eks-mcp-server

# Configure AWS credentials, then integrate into your AI assistant:
# For Cursor: uvx awslabs.eks-mcp-server@latest --allow-write --allow-sensitive-data-access
# For VS Code: same uvx command in MCP settings

import boto3
from awslabs.eks_mcp_server import EKSMCPServer

Requires Python 3.10+, AWS CLI configured with credentials, and IAM permissions (read-only or write operations depending on use case). Kubernetes API access requires either cluster creator status or an EKS Access Entry configured for your IAM principal.

Verify before relying

• Whether the package works with AI assistants other than Kiro, Cursor, and VS Code
• Performance characteristics when managing large clusters or high-volume resource operations
• Compatibility with kubeconfig-based authentication in all supported Python versions

Package facts

Evidence: awslabs_eks_mcp_server-0.1.37-py3-none-any.whl

Tags

More Software Development packages

Further reading