MCP servers and skills: search, filter by where they run, and compare.
1–27 of 27 tools for “eks”
Clear allAWS Labs MCP server for Amazon EKS clusters, run locally over stdio.
OfficialPythonApache-2.0★ 9.8kNeeds AWS
AI-powered Amazon EKS cluster management and troubleshooting
PythonNo licenseFew starsNo key
A comprehensive toolkit for deploying production-ready Generative AI infrastructure on Amazon EKS. Includes pre-configured components for: 🚀 AI Gateway (LiteLLM) 🤖 LLM Serving (vLLM, SGLang, Ollama)
OfficialSkillMIT-0★ 96No key
Comprehensive, scalable ML inference architecture using Amazon EKS, leveraging Graviton processors for cost-effective CPU-based inference and GPU instances for accelerated inference. Guidance provides
SkillMIT-0★ 19No key
Diagnose and remediate cluster-wide HyperPod (EKS or Slurm) problems — creation / deployment failures (CloudFormation, EFA health check, lifecycle scripts, capacity), EKS access, node replacement, Clo
OfficialSkillApache-2.0★ 918 in collectionNo key
Generate comprehensive issue reports from HyperPod clusters (EKS and Slurm) by collecting diagnostic logs and configurations for troubleshooting and AWS Support cases. Use when users need to collect d
OfficialSkillApache-2.0★ 918 in collectionNo key
Diagnose NCCL failures and adjacent training-pod failures on HyperPod GPU clusters (EKS or Slurm) — training hangs, AllReduce / collective-op timeouts, EFA or libfabric errors, rendezvous failures, EF
OfficialSkillApache-2.0★ 918 in collectionNo key
Deploy to AWS Elastic Beanstalk, in either Beanstalk Standard mode (EC2) or Beanstalk Cluster mode (managed EKS). Triggers on: elastic beanstalk, EB, beanstalk standard, beanstalk cluster, managed EC2
OfficialSkillApache-2.0★ 918 in collectionNo key
Query AWS resources using natural language. Covers EC2, S3, RDS, Lambda, ECS, EKS, Secrets Manager, IAM, VPC, networking, messaging, and more. Strictly read-only — no writes, deletes, or mutations.
OfficialSkillMIT★ 40k in collectionNo key
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. Covers on-node EFA, GPU / accelerator hardware (XID
OfficialSkillApache-2.0★ 918 in collectionNo key
Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for multi-node distributed training. Use when running on EKS /
OfficialSkillApache-2.0★ 3.6k in collectionNo key
AI/ML and HPC at planetary scale. One API. Every Accelerator. Any Region. MIT-0 licensed
in the readmeGlobal Capacity Orchestrator Guidance for EKS AutoMode Clusters with Global Capacity Orchestrator on AWS Official AWS Solutions Guidance One API. Every Accelerator. Any Region. Quick Start
PythonMIT-0★ 49No key
Setting up and running Qdrant Hybrid Cloud on your own Kubernetes cluster (managed, on-prem, or edge): prerequisites, storage/CSI and backups, installing the Qdrant Cloud agent and operator, creating/
in the skill textHybrid Cloud on their own infrastructure; is running Qdrant on their own EKS, GKE, AKS, OpenShift, or other Kubernetes; asks about the agent or operator
OfficialSkillApache-2.0★ 256 in collectionNo key
Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding a
in the readmeopen source, licensed under Apache 2.0, and runs on Kubernetes (Amazon EKS), fully managed serverless (Amazon ECS), or Docker Compose (Amazon EC2). It began
SkillApache-2.0★ 981No key
Cloud architecture diagrams in both directions: AI prompt or JSON to diagram, diagram to Terraform via MCP server, and Terraform to diagram via CLI or CI/CD. Using Official AWS, Azure and GCP icons.
in the readmeAzure three-tier web app Google Cloud three-tier web app AWS EKS with Karpenter Azure hub-and-spoke landing zone Google Cloud GKE with Private
PythonAGPL-3.0★ 1.7kNo key
一款轻量级、跨平台的 Mini Kubernetes AI Dashboard，支持大模型+智能体+MCP(支持设置操作权限)，集成多集群管理、智能分析、实时异常检测等功能，支持多架构并可单文件部署，助力高效集群管理与运维优化。
in the readme主要特点 - **迷你化设计**：所有功能整合在一个单一的可执行文件中，部署便捷，使用简单。 - **简便易用**：友好的用户界面和直观的操作流程，让 Kubernetes 管理更加轻松。支持标准k8s、aws eks、k3s、kind、k0s等集群类型。 - **高效性能**：后端采用 Golang 构建，前端基于百度 AMIS，保证资源利用率高、响应速度快。 - **AI驱动融合** ：基于ChatGPT实现划词解释
GoMIT★ 886No key
Jump Skill Ninjas are intelligent meta-skills — master orchestrators that route your requests to the most appropriate specialized skill from a curated library. Instead of manually searching through hu
in the skill textalways route you to the right specialist. ``` ┌─────────────────────────────────────────────────────────────────────────┐ │ YOUR REQUEST │ │ "Set up an EKS cluster with │ │ Karpenter for autoscaling" │ └─────────────────────────────────────────────────────────────────────────┘ │ ▼ ┌───────────────
SkillMIT★ 33No key
MCP server exposing all Helm CLI capabilities via the Model Context Protocol (Helm v3 + v4)
in the readmemodes** — stdio (default) and Streamable HTTP, stateless by default - **Cloud provider ready** — EKS, GKE, AKS kubeconfig formats work out of the box - **Security first** — Linux process
PythonMIT★ 2Few starsNo key
A GitOps Model Context Protocol (MCP) Server.
in the readmeusing an API key. ## Prerequisites - Go 1.20+ - Docker - Kubernetes cluster & valid `~/.kube/config` - EKS cluster with AWS_PROFILE set locally - ArgoCD credentials - GitLab personal access token - Claude
GoMIT★ 9No key
A curated collection of persona-based mcp server & tool groupings.
in the readmeservers individually | `"persona": "python-backend-engineer"` ✨ | | **DevOps Engineer** | Configure AWS CLI + CloudFormation + EKS + Docker + Postgres + DynamoDB separately | `"persona": "aws-cloud-engineer"` ✨ | | **Database Admin** | Set up Postgres
SkillMIT★ 39No key
Enterprise MCP Server Management
in the readmeand private-cloud Kubernetes deployments**. If you're on a managed cloud (EKS / GKE / AKS), the chart works there too — see the last appendix. > **Sizing.** The
SkillApache-2.0★ 1Few starsNo key
Architecture diagrams as code: a JSON topology spec in, an editable Excalidraw diagram out. MCP server and CLI, on npm.
in the readmegroups": [ { "id": "aws", "label": "AWS eu-north-1" }, { "id": "k8s", "label": "EKS", "parent": "aws" } ], "nodes": [ { "id": "web", "label": "Web app", "kind": "client" }, { "id": "api", "label": "Order
Node.jsMITFew starsNo key
in the readmeService (ECS)**: If using ECS, review ECS service quotas - **Elastic Kubernetes Service (EKS)**: If using EKS, review EKS service quotas - **Network bandwidth**: Ensure sufficient network bandwidth
OfficialSkillApache-2.0★ 718No key
Kubernetes Skill for Claude Code and Codex. LLMs hallucinate a lot with K8s - KubeShark fixes this. It eliminates hallucinations and grounds your Kubernetes, Helm etc official best practices.
in the skill textStep 2) | No | | **Output contract** | Yes -- assumptions, tradeoffs, rollback | No | | **Conditional references** | EKS, GKE, AKS, OpenShift, GitOps, observability stacks | No | | **Security-first defaults** | PSS restricted profile
SkillMIT★ 450No key
kom 是一个用于 Kubernetes 操作的工具，SDK级的kubectl、client-go的使用封装。并且支持作为管理k8s 的 MCP server。 它提供了一系列功能来管理 Kubernetes 资源，包括创建、更新、删除和获取资源，甚至使用SQL查询k8s资源。这个项目支持多种 Kubernetes 资源类型的操作，并能够处理自定义资源定义（CRD）。 通过使用 kom，你可以轻松
in the readme注册一个名为default的集群，那么kom.DefaultCluster()则会返回该集群。 kom.Clusters().RegisterByPathWithID("/Users/kom/.kube/config", "default") ``` #### 注册AWS EKS集群 ```go // 配置 EKS 集群信息 config := aws.EKSAuthConfig{ AccessKey: "XXX", // AWS Access Key ID SecretAccessKey: "yyy", // AWS Secret
GoMIT★ 151No key
A platform engineering handbook covering Kubernetes, OpenShift, Argo CD, Flux CD, AWS, Azure, Terraform, and GitHub Actions — with an optional Claude plugin layer for interactive guidance.
in the skill textResourceSets , MCP , Terraform bootstrap — `/platform-skills:fluxcd` | | AWS | references/aws.md | IAM least-privilege, IRSA, EKS, resource tagging, cost allocation | | AWS CloudFront | references/aws-cloudfront.md | Distributions, OAC, cache policies, security headers
SkillApache-2.0★ 69No key
K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kuber
in the readmeabout your clusters without leaving the Claude interface. > **Cloud Providers**: For AWS EKS, GKE, or Azure AKS, you'll need additional configuration. See the Cloud Provider
SkillMIT★ 212No key
Who stands behind it
Who stands behind it
