kubeaid-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KUBECONFIG | No | Path to the kubeconfig file. | ~/.kube/config |
| KUBEAID_CONTEXT | No | Pin a fixed default context. Omit it to track current-context live. | |
| KUBEAID_ALLOW_EXEC | No | Expose exec_command (run commands in containers). | false |
| KUBEAID_ALLOW_WRITES | No | Expose the mutating tools (apply/patch/delete/scale/rollout). | false |
| KUBEAID_REQUEST_TIMEOUT | No | Per-request timeout for Kubernetes API calls (e.g. 30s, 1m, or milliseconds). | 30s |
| KUBEAID_PROTECTED_CONTEXTS | No | Comma-separated contexts that may never be written to or exec'd into. |
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_contextsA | List the kubeconfig contexts (clusters) this server can target. The one marked isDefault is used when a tool call omits the context parameter. |
| list_namespacesA | List all namespaces in the Kubernetes cluster, with their status. |
| list_podsA | List pods in a namespace (or across all namespaces if omitted), with derived status, ready count, restarts and age. |
| describe_podA | Describe a pod: its status, per-container state (including waiting/termination reasons and last restart), and recent events. Use this to diagnose why a pod is not healthy. |
| get_pod_logsA | Fetch the tail of a pod's container logs. Set previous=true to read logs from a crashed container's prior instance. |
| list_deploymentsA | List deployments in a namespace (or across all namespaces if omitted), with ready/up-to-date/available replica counts and age. |
| list_nodesA | List cluster nodes with Ready status, roles, age, kubelet version and internal IP. |
| get_eventsA | List recent events in a namespace (or across all namespaces if omitted), sorted oldest to newest. Warning-type events surface cluster problems. |
| describe_resourceA | Fetch any Kubernetes resource by kind and name, including custom resources (CRDs). Returns the resource object with noise (managedFields, last-applied annotation) stripped. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| diagnose_pod | Diagnose why a pod is unhealthy and suggest a fix, using the kubeaid tools. |
| triage_namespace | Triage the health of a whole namespace: find unhealthy workloads and investigate each. |
| cluster_health_check | Run a high-level health check across the whole cluster. |
| review_warnings | Review recent Warning events and explain what they mean. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Health Checks | Current health status of all registered health checks |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
TDQS
Scored across 9 tools
Every tool targets a distinct Kubernetes resource or action (e.g., describe_pod vs describe_resource, list_pods vs list_deployments), with no overlapping purposes.
All tools follow a consistent verb_noun pattern with lowercase and underscores (e.g., list_pods, get_events, describe_resource), making them predictable and easy to differentiate.
With 9 tools, the surface is lean yet comprehensive for a diagnostic Kubernetes MCP server, covering essential inspection operations without unnecessary bloat.
The tool set covers core diagnostic workflows—listing, describing, logs, events—but misses operational actions like exec, port-forward, or resource creation. Minor gap given the diagnostic focus.