Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Multi-Cloud Kubernetes & OpenShift Deploy Pro

    1

    Manage production container workloads across Red Hat OpenShift (Routes, DeploymentConfigs) and cloud-managed Kubernetes (AWS EKS, Azure AKS, Google GKE).

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Multi-Cloud Kubernetes & OpenShift Deploy Pro

    Multi-Cloud Kubernetes & OpenShift Deploy Pro

    Example session with this skill installed

    Check the health of the 'api-gateway' pods in the 'production' namespace and show the logs for any containers that have restarted.

    • Read your context and instructions
    • Compiled the multi-cloud kubernetes

    I have analyzed the health of the api-gateway workload in the production namespace. One pod is currently experiencing issues.

    Pod Health and Diagnostics: production/api-gateway

    Pod NamePhaseRestartsLast ReasonStatus
    api-gateway-7f8d9b-x2k4Running4OOMKilledCrashLoopBackOff
    api-gateway-7f8d9b-l9m1Running0N/AReady

    Container Logs (Previous Instance: api-gateway-7f8d9b-x2k4)

    2023-10-27T10:15:02.123Z INFO  Initializing application...
    2023-10-27T10:15:05.456Z INFO  Connecting to database...
    2023-10-27T10:15:08.789Z ERROR Fatal: Memory limit exceeded during cache warming.
    2023-10-27T10:15:08.790Z INFO  Shutting down...
    

    Warning Events

    • Type: Warning | Reason: BackOff | Message: Back-off restarting failed container
    • Type: Warning | Reason: InspectFailed | Message: Failed to apply resource limits

    Analysis
    The pod api-gateway-7f8d9b-x2k4 was terminated due to OOMKilled. The logs confirm the process hit memory limits during the cache warming phase. The restart loop is triggered by the application failing to initialize within the allocated memory quota.

    Next steps

    1. Check the resource limits in the deployment spec via k8s_list_deployments_and_configs.
    2. Increase the memory limit for the api-gateway container if the cache size is expected.
    3. Review the k8s_get_cluster_overview to ensure node resources are available for scaling.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    🚀 Production Workflows

    1. Multi-Cluster Discovery & Route Inspection: Audits ingress traffic, OpenShift routes, TLS configurations, and cluster capacity across multiple cloud accounts.
    2. Immutable Container Digest Rollouts: Deploys cryptographically verified image@sha256:... digests, monitoring rolling update progress until all pods report healthy.
    3. CrashLoopBackOff & OOMKilled Triage: Extracts previous container crash logs, termination exit codes, and K8s warning events in a single step.
    4. Emergency One-Click Rollback: Instantly restores previous deployment revisions upon failed canary checks or health probe failures.
    5. Fleet Scaling & Pod Restarts: Safely scales deployment replicas and performs rolling restarts.

    🛡️ Safety & Governance

    • Read-only autonomous cluster inspection, log retrieval, and route mapping.
    • Confirmation-gated rollouts, scaling, pod terminations, and rollbacks.

    Launch via: uvx k8s-cloud-deploy-mcp (or uvx k8s-mcp)

    Requires pre-configured Kubeconfig and environment variables. Cloud provider credentials must be set externally. Mutative deployments reject mutable tags like 'latest'.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    Requires

    Python
    K8s Cloud Deploy MCP
    uv (Python tool runner)
    K8s MCP

    Permissions

    Terminal / Shell
    Write Files
    Environment Variables
    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the discovery, health triage, and deployment of workloads across EKS, AKS, GKE, and Red Hat OpenShift clusters via a standardized MCP server. It specifically solves the risks of manual Kubernetes management by enforcing immutable image digests and mandatory confirmation gates for all mutations.

    Yes, the skill includes specialized tools for OpenShift-specific API groups, allowing you to audit TLS termination policies, inspect route admission status, and manage project-specific workloads on platforms like ROSA and ARO.

    The skill requires a pre-configured `kubeconfig` on your local machine or server. It uses your existing context and permissions, so you must ensure your environment variables and cloud provider credentials (like AWS or Azure CLI) are active before initiating a session.

    To prevent 'tag drift' and ensure production stability, the skill's mutation tools are hardcoded to reject mutable tags like `:latest` or `:stable`. You must provide the unique SHA256 image digest to trigger a deployment or rollout.

    The skill acts as an interface between your AI agent and your cluster; it does not store or transmit your cloud passwords or Kubeconfig secrets to any external servers. All operations are executed within your authenticated local environment.

    You receive the full MCP server implementation optimized for Kubernetes and OpenShift management. This includes the complete toolset for cluster discovery, health triage, route inspection, and the safety-gated deployment workflow.

    New in DevOps & Cloud