homelab-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOMELAB_MCP_CONTEXT | No | kubeconfig context to use | current-context |
| HOMELAB_MCP_READONLY | No | 1/true disables all mutating tools | 0 |
| HOMELAB_MCP_MAX_REPLICAS | No | Upper bound for scale_deployment | 10 |
| HOMELAB_MCP_MUTABLE_NAMESPACES | No | Namespaces mutations may touch; * = all | default,apps,monitoring,ci |
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 |
|---|---|
| cluster_summaryA | Node and pod health totals plus the list of unhealthy pods. Start here. |
| list_podsA | List pods (optionally one namespace). Unhealthy pods sort first. |
| list_deploymentsC | List deployments with ready/desired replica counts. |
| list_eventsC | Recent cluster events; Warning-type events sort first. |
| pod_logsC | Tail a pod's logs. |
| node_healthB | Per-node readiness, kubelet version, capacity, and pressure conditions. |
| restart_deploymentB | Rollout-restart a deployment (subject to the mutable-namespace allowlist). |
| scale_deploymentB | Scale a deployment to N replicas (0..max), subject to the allowlist. |
| delete_podB | Delete a pod so its controller recreates it (subject to the allowlist). |
| server_infoB | Report the effective configuration (context, read-only, allowlist). |
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 10 tools
Each tool targets a distinct aspect of cluster management: summary, pods, deployments, events, nodes, logs, scaling, restart, and configuration. No overlapping purposes.
Tools use a mix of verb_noun (delete_pod, list_deployments) and noun_noun (cluster_summary, node_health) patterns. While mostly clear, the inconsistency may cause minor confusion for an agent.
10 tools provide a well-scoped set for monitoring and managing a Kubernetes cluster, covering essential operations without being overwhelming.
Covers core observability and common actions (restart, scale, delete pod) but lacks CRUD for deployments and pods, leaving gaps for full lifecycle management.