Kubernetes Read-Only MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_clustersA | List contexts and kubeconfig files skipped due to duplicate contexts. |
| list_api_resourcesC | Discover Kubernetes API resources, including CRDs, that can be queried. |
| list_crdsB | List all installed CustomResourceDefinitions and their served versions. |
| list_resourcesB | List any Kubernetes resource kind using apiVersion/kind discovery. |
| get_resourceB | Get any Kubernetes resource object by apiVersion, kind and name. |
| get_cluster_healthB | Get Kubernetes version and a summary of node readiness for one context. |
| list_nodesB | List nodes with readiness, roles, version and pressure conditions. |
| list_namespacesB | List namespaces and their phases. |
| list_podsB | List Pods, optionally restricting results to Pods with failure signals. |
| describe_podA | Return detailed status, container state and conditions for a Pod. |
| get_pod_logsA | Read a bounded tail of container logs. Logs may contain sensitive application data. |
| list_deploymentsB | List Deployments and replica readiness. |
| list_statefulsetsA | List StatefulSets and replica readiness. |
| list_eventsB | List recent warning and normal Kubernetes events, newest first. |
| list_storageB | List PersistentVolumeClaims, PersistentVolumes and StorageClasses. |
| list_rbacB | List Roles, RoleBindings, ClusterRoles and ClusterRoleBindings as metadata. |
| get_configmapA | Read a ConfigMap including its data. Review returned data for sensitive values. |
| list_secretsA | List Secret metadata only; secret values are never returned. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 18 tools
Most tools target clearly distinct resource areas, but list_api_resources, list_crds, and list_resources have similar names and overlapping discovery/list purposes. Generic list/get tools also overlap with specialized listers, though descriptions clarify their intended use.
All tools consistently use lowercase snake_case verb_noun naming: list_* for collections, get_* for single objects and logs, and describe_pod for detailed pod status. No mixed conventions or unpredictable patterns.
18 tools is slightly above the typical 3-15 well-scoped range, but the breadth of Kubernetes read-only scenarios justifies the count. Each tool addresses a meaningful area and the overlap is modest.
The surface covers cluster health, discovery, common workloads, events, storage, RBAC, and secrets, with generic list_resources/get_resource filling gaps for resource types without dedicated tools. Missing convenience getters for services, ingresses, and jobs, but no dead ends exist.