Kom — Kubernetes Operations Manager

What it is

A Go library that wraps kubectl and client-go, with an MCP server built into it. You start the server from your own program — mcp.RunMCPServer("kom mcp server", "0.0.1", 9096) — and the compiled binary is the stdio entry point your client launches — Claude Desktop, Cursor, Windsurf and Cherry Studio all take it that way. The README also names http://IP:9096/sse as an SSE endpoint, but RunMCPServer opens that listener only after its stdio session ends; a standing SSE server is started with RunMCPServerWithOption and Mode: mcp.ServerModeSSE, as the repository's own main.go does. Every tool takes a cluster, namespace and name, so one server front-ends every cluster you registered, self-managed or AWS EKS.

What you get

• Cluster registry — list_k8s_clusters, and in SSE mode register_k8s_cluster and unregister_k8s_cluster at runtime, so a new kubeconfig does not mean a restart
• Any resource, custom ones included — get_k8s_resource, describe_k8s_resource, list_k8s_resource, delete_k8s_resource, patch_k8s_resource, label_k8s_resource, annotate_k8s_resource
• The whole Deployment lifecycle — scale_k8s_deployment, restart_k8s_deployment, stop_k8s_deployment, restore_k8s_deployment, update_k8s_deployment_image_tag, get_k8s_deployment_hpa_list
• Rollouts as separate calls rather than one blunt apply — get_k8s_deployment_rollout_history, undo_k8s_deployment_rollout, pause_k8s_deployment_rollout, resume_k8s_deployment_rollout, get_k8s_deployment_rollout_status
• Pod inspection and Pod insides — list_k8s_pod, describe_k8s_pod, get_k8s_top_pod, GetPodLogsTool, run_command_in_k8s_pod, and file work with list_files_in_k8s_pod, list_pod_all_files, UploadPodFileTool, DeletePodFileTool
• What a Pod is wired to — get_k8s_pod_linked_services, get_pod_linked_ingresses, get_pod_linked_endpoints, get_k8s_pod_linked_env, get_pod_linked_env_from_yaml
• Node scheduling and capacity — cordon_k8s_node, uncordon_k8s_node, drain_k8s_node, taint_k8s_node, untaint_k8s_node, get_k8s_node_resource_usage, get_k8s_node_ip_usage, get_k8s_top_node, get_k8s_pod_count_running_on_node
• Manifests in and out — apply_k8s_yaml, delete_k8s_yaml
• Storage and Ingress defaults — set_k8s_default_storageclass, get_k8s_storageclass_pvc_count, get_k8s_storageclass_pv_count, set_default_k8s_ingressclass
• Events where you need them — list_k8s_event, list_k8s_deploy_event, list_k8s_pod_event, plus restart_k8s_daemonset

Requirements

Go, and cluster credentials. This is a library rather than a published binary: you write a Go main, register your clusters and call RunMCPServer, then go build main.go. KUBECONFIG is the default source of credentials; RegisterInCluster() picks up in-cluster credentials, RegisterByPathWithID takes a kubeconfig path plus an ID, RegisterByTokenWithServerAndID takes a bearer token, API server address and cluster ID with the CA certificate as an optional register-time option, and RegisterAWSCluster takes an aws.EKSAuthConfig carrying AccessKey, SecretAccessKey, Region and ClusterName. In SSE mode kubeconfigs can instead be listed in mcp.ServerConfig or auto-discovered from a directory with LoadKubeconfigsFromDirectory. Whatever RBAC the credential carries is what the tools can do, and the set includes delete_k8s_resource, drain_k8s_node and run_command_in_k8s_pod — scope the service account to the namespaces you want reachable before you register it.

Setup effort

Follow the published steps

Tools you get

60 tools registered in the project's code. The README's tool table says 59, but seven of its rows give Go function names such as GetPodLogsTool instead of the registered names, and it omits register_k8s_cluster, unregister_k8s_cluster, list_k8s_namespace and five pod tools.

Requires

• Go toolchain (go build)
• A Kubernetes cluster and a kubeconfig (KUBECONFIG)

Where it runs

All 4 documented clients run the server on your machine.