Run Kubernetes cluster operations through MCP
Use mcp-server-kubernetes so an MCP-capable agent can inspect, troubleshoot, and manage Kubernetes resources through a configured kubeconfig.
npx skills add agentskillexchange/skills --skill run-kubernetes-cluster-operations-through-mcp
Use mcp-server-kubernetes when an MCP-capable agent needs controlled access to Kubernetes cluster state and management commands: list resources, inspect pods, read logs and events, work with namespaces and contexts, and assist with Helm-backed operations from an existing kubeconfig. The operator verifies kubectl access first, adds the MCP server to the client, scopes credentials to the intended cluster, and asks the agent for a concrete diagnostic, deployment, or cluster-management task. Inputs are kubectl, kubeconfig credentials, optional Helm, and the MCP client configuration; outputs are Kubernetes inspection results, command-backed remediation plans, resource changes when authorized, and evidence from cluster APIs. The scope boundary is Kubernetes operations through the upstream MCP server, not a generic Kubernetes tutorial, kubectl wrapper, or broad DevOps platform listing.
What this skill actually does
Inputs and prerequisites: MCP-compatible client, kubectl, valid kubeconfig, Kubernetes cluster access, and optional Helm v3.
Setup notes: Verify kubectl can reach the intended cluster, then add the server to an MCP client. For Claude Code, run claude mcp add kubernetes — npx mcp-server-kubernetes. For other clients, configure the command npx mcp-server-kubernetes and provide the intended kubeconfig context.
Source and verification boundary: use https://github.com/Flux159/mcp-server-kubernetes as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.