eks-mcp-server

Configure an MCP server connection for live EKS cluster operations.

39|14|Updated Mar 23, 2026
One-click install
npx skills add https://github.com/aws-samples/sample-apex-skills --skill eks-mcp-server
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: eks-mcp-server
Source: https://github.com/aws-samples/sample-apex-skills/tree/main/skills/eks-mcp-server
Command: npx skills add https://github.com/aws-samples/sample-apex-skills --skill eks-mcp-server

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you set up an MCP server so your AI assistant can perform real, live operations against your EKS clusters instead of being limited to offline guidance.

Core Features & Use Cases

  • Choose deployment mode: Configure either AWS-hosted (managed, minimal ops) or self-hosted (local, flexible auth) EKS MCP Server.
  • Wire tools into your assistant: Add the MCP server configuration to your IDE/CLI assistant so EKS tools appear and work.
  • Verify and hand off to MCP tools: Restart the assistant, confirm tool availability (for example, listing clusters), then proceed with actual cluster operations through the MCP tools.

Example use case: You need an assistant to list your EKS clusters, inspect pods, and troubleshoot workloads, but you want those actions to run against the live cluster through MCP.

Quick Start

Tell your AI: “Set up EKS MCP for my environment and configure my assistant so I can list my EKS clusters.”

Frequently Asked Questions about eks-mcp-server

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I connect my AI assistant to live EKS cluster operations?

To connect an AI assistant to live EKS clusters, you set up an MCP server configuration that bridges your IDE or CLI assistant with real cluster resources, enabling actions like listing clusters and inspecting pods directly.

What is the difference between AWS-hosted and self-hosted EKS MCP Server deployment?

AWS-hosted EKS MCP Server provides a managed experience with minimal operational overhead, while self-hosted deployment runs locally and offers flexible authentication using your existing kubeconfig and IAM permissions setup.

How can I configure my assistant to use EKS MCP tools for troubleshooting Kubernetes workloads?

You configure your assistant by mapping the MCP server configuration entries into your IDE or CLI settings, then restart the assistant to verify tool availability before proceeding to troubleshoot pods and validate workloads.

What IAM or kubeconfig prerequisites are needed before setting up EKS MCP?

Before setting up EKS MCP, you must ensure your environment has valid kubeconfig credentials and appropriate IAM permissions configured to authorize live operations against your target EKS clusters.

Does EKS MCP support automated deployment and validation of workloads through AI?

Yes, EKS MCP supports automated deployment and validation by allowing your AI assistant to perform live operations against EKS clusters, executing actions like workload deployment and status verification through configured MCP tools.

Why are my EKS MCP tools not showing up after configuration?

If EKS MCP tools are not showing up, you likely need to restart your AI assistant to refresh the tool registry, then verify the configuration entries are correctly mapped and your IAM prerequisites are satisfied.