MCP Server Kubernetes
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS | No | Run the server in a non-destructive mode that disables all destructive operations (delete pods, delete deployments, delete namespaces, etc.). Set to "true" to enable. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cleanupC | Cleanup all managed resources |
| kubectl_getA | Get or list Kubernetes resources by resource type, name, and optionally namespace |
| kubectl_describeA | Describe Kubernetes resources by resource type, name, and optionally namespace |
| kubectl_applyC | Apply a Kubernetes YAML manifest from a string or file |
| kubectl_deleteB | Delete Kubernetes resources by resource type, name, labels, or from a manifest file |
| kubectl_createC | Create Kubernetes resources using various methods (from file or using subcommands) |
| kubectl_logsB | Get logs from Kubernetes resources like pods, deployments, or jobs |
| kubectl_scaleB | Scale a Kubernetes deployment |
| kubectl_patchB | Update field(s) of a resource using strategic merge patch, JSON merge patch, or JSON patch |
| kubectl_rolloutB | Manage the rollout of a resource (e.g., deployment, daemonset, statefulset) |
| kubectl_contextB | Manage Kubernetes contexts - list, get, or set the current context |
| explain_resourceB | Get documentation for a Kubernetes resource or field |
| install_helm_chartA | Install a Helm chart with support for both standard and template-based installation |
| upgrade_helm_chartC | Upgrade an existing Helm chart release |
| uninstall_helm_chartC | Uninstall a Helm chart release |
| node_managementB | Manage Kubernetes nodes with cordon, drain, and uncordon operations |
| port_forwardC | Forward a local port to a port on a Kubernetes resource |
| stop_port_forwardD | Stop a port-forward process |
| exec_in_podA | Execute a command in a Kubernetes pod or container and return the output. Command must be an array of strings where the first element is the executable and remaining elements are arguments. This executes directly without shell interpretation for security. |
| list_api_resourcesC | List the API resources available in the cluster |
| kubectl_genericB | Execute any kubectl command with the provided arguments and flags |
| pingA | Verify that the counterpart is still responsive and the connection is alive. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| k8s-diagnose | Diagnose Kubernetes Resources. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Kubernetes Pods | List of pods in the default namespace |
| Kubernetes Deployments | List of deployments in the default namespace |
| Kubernetes Services | List of services in the default namespace |
| Kubernetes Namespaces | List of all namespaces |
| Kubernetes Nodes | List of all nodes in the cluster |
TDQS
Scored across 22 tools
Most tools target distinct Kubernetes verbs or resources, but kubectl_create, kubectl_apply, and kubectl_patch overlap in resource creation/update, and kubectl_generic acts as a catch-all that duplicates every other kubectl tool. cleanup is also vaguely scoped relative to delete and uninstall operations.
Core tools use a consistent kubectl_ prefix with snake_case, but the set mixes prefixes (helm_* and no prefix), patterns like verb_noun (install_helm_chart), noun phrases (node_management), and bare verbs (cleanup, ping). Readable but not predictable across the whole set.
22 tools is on the heavy side but each covers a meaningful Kubernetes or Helm operation across resource lifecycle, node management, port forwarding, and exec. The existence of kubectl_generic makes some dedicated tools redundant, yet the count remains reasonable for the domain's breadth.
The surface covers core resource lifecycle (get, describe, create, apply, delete, patch, scale, rollout), Helm install/upgrade/uninstall, node management, port forwarding, exec, and context, with kubectl_generic as a fallback. Minor gaps like Helm list/rollback exist, but agents can work around most with generic commands.