devops-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for SSE mode (default: 3000) | |
| LOKI_URL | No | Loki server URL | |
| KUBECONFIG | No | Path to Kubernetes kubeconfig file (optional, omit for in-cluster service account) | |
| LOKI_TOKEN | No | Optional: Loki API token | |
| K8S_CONTEXT | No | Optional: Pin a specific kubeconfig context | |
| ARGOCD_TOKEN | No | ArgoCD API token | |
| ARGOCD_SERVER | No | ArgoCD server URL | |
| MCP_AUTH_TOKEN | No | Bearer token for SSE authentication | |
| PROMETHEUS_URL | No | Prometheus server URL | |
| PAGERDUTY_TOKEN | No | PagerDuty API v2 token | |
| DEVOPS_MCP_DRY_RUN | No | Set to 'true' to block all mutations globally | |
| DEVOPS_MCP_AUDIT_LOG | No | File path for audit log (JSONL format) | |
| K8S_ALLOWED_NAMESPACES | No | Optional: Comma-separated list of allowed namespaces | |
| PROMETHEUS_BEARER_TOKEN | No | Optional: Bearer token for authenticated Prometheus |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| k8s__list_podsB | List pods with status, restarts, node, and age |
| k8s__get_pod_logsC | Get logs from a pod container |
| k8s__describe_resourceC | Full describe for any resource type |
| k8s__get_eventsC | Cluster or namespace events, filterable by reason |
| k8s__list_deploymentsC | Deployments with replica counts and rollout health |
| k8s__get_resource_usageC | CPU/mem usage per pod via metrics-server |
| k8s__list_contextsB | All kubeconfig contexts and the active one |
| k8s__switch_contextC | Switch active context (session-scoped) |
| k8s__scale_deploymentC | Scale replicas with dry-run diff preview |
| k8s__rollout_restartC | Trigger rolling restart of a deployment |
| k8s__apply_manifestC | Apply a manifest string with server-side dry-run |
| k8s__delete_resourceC | Delete a named resource — requires confirm: true |
| k8s__get_node_statusB | Get node status with conditions, capacity, allocatable, labels, and taints |
| k8s__get_network_policiesA | List network policies with podSelector, ingress/egress rules |
| k8s__get_ingressesA | List ingresses with hosts, paths, backends, and TLS config |
| k8s__diff_resourceB | Compare current resource state against last-applied-configuration annotation to show drift |
| k8s__list_cronjobsA | List cronjobs with schedule, suspend status, active jobs, and last run times |
| k8s__get_cronjob_statusB | Detailed status of a specific cronjob including recent job history |
| k8s__list_servicesA | List services with type, clusterIP, ports, selector, and externalIPs |
| k8s__list_pvcsA | List PersistentVolumeClaims with status, capacity, accessModes, and storageClass |
| k8s__get_hpaA | Get HorizontalPodAutoscaler details with metrics, replicas, and conditions |
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 21 tools
Each tool targets a distinct resource-action pair with clear descriptions. For example, list_pods, get_pod_logs, and describe_resource are all distinct. No overlapping functionality.
All tools follow the pattern `k8s__verb_noun`. Verbs are consistent (list, get, describe, etc.), but there is minor inconsistency in singular vs plural nouns (e.g., get_pod_logs vs list_pods). Overall pattern is strong.
21 tools cover a wide range of Kubernetes operations from monitoring to management. The count is slightly on the high side but well-scoped for a comprehensive DevOps tool.
Covers many common tasks (viewing, scaling, applying manifests) but lacks explicit create/update operations for many resource types (beyond apply). Missing rollback, secrets/configmaps, and other lifecycle operations.