kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.
The Kubernetes MCP server (Flux159's implementation is the established community choice) connects your assistant to any cluster your kubeconfig can reach, wrapping the kubectl verbs that fill an SRE's day: get, describe, logs, events, exec, scale, apply, plus Helm operations for chart management.
Its best genre is the production whodunit. "Why is checkout-service crash-looping?" kicks off an actual investigation — pod status, then events, then logs, then resource limits — with the assistant following the evidence across objects the way a human operator would, except it reads faster and never forgets to check the events. For the recurring classics (ImagePullBackOff, OOMKilled, pending pods with unsatisfiable node selectors) it's remarkably effective at going from symptom to root cause in one exchange.
Cluster comprehension is the second win. Inherited clusters, like inherited codebases, hide their logic; "map what's running in the payments namespace and how services connect" produces the orientation document nobody wrote. Routine operations — scaling deployments, restarting rollouts, port-forwarding for a quick check — are all present too.
It being able to do things is also the caution: exec, apply and delete are in the toolset, and kubeconfig context is your blast-radius control. Point it at staging with a read-heavy role first; a non-destructive mode flag exists and is worth using anywhere important. RBAC applies as it would to any client, so the cluster-side guardrails you already have keep working.
ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS=true strips the delete-class tools while leaving get, describe, logs and events intact — everything an investigation needs and nothing an accident needs.port_forward opens a real local port that outlives the tool call. Close forwards when you are done, particularly ones pointed at a database service.Status → events → logs → limits, investigated end-to-end in one ask.
Namespaces, workloads and service relationships mapped for humans.
Scaling, restarts and quick port-forwards without leaving the conversation.
| Tool | What it does |
|---|---|
| kubectl_get / kubectl_describe | List and inspect any resource type |
| kubectl_logs | Read pod/container logs |
| kubectl_apply / kubectl_delete | Apply manifests and remove resources |
| kubectl_scale / kubectl_rollout | Scale deployments and manage rollouts |
| exec_in_pod | Run commands inside containers |
| install_helm_chart / upgrade_helm_chart | Helm chart operations |
| port_forward | Forward a local port to a pod or service |
{
"mcpServers": {
"kubernetes": {
"command": "npx",
"args": ["-y", "mcp-server-kubernetes"]
}
}
}Uses your current kubeconfig context — switch contexts to control which cluster it sees. Set ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS=true for a safe mode.
Node.js 18+ and a working kubeconfig. RBAC and context selection are your safety controls; safe mode available via env flag.
| Variable | Description | Required |
|---|---|---|
| ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS | Disable delete/exec-class tools for a read-safe modee.g. true | Optional |
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.