Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
ARGOCD_TOKENAPI keyoptionalArgoCD authentication token
PROMETHEUS_BEARER_TOKENAPI keyoptionalPrometheus bearer token
PAGERDUTY_TOKENAPI keyoptionalPagerDuty API token
LOKI_TOKENAPI keyoptionalLoki authentication token
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
argo__list_appsAll apps with health, sync status, source repoAll apps with health, sync status, source repo
No input schema was published for this tool.
argo__get_appFull spec and status for one applicationFull spec and status for one application
No input schema was published for this tool.
argo__get_app_diffLive diff between git and cluster stateLive diff between git and cluster state
No input schema was published for this tool.
argo__get_app_historyDeployment history with git SHAs and timestampsDeployment history with git SHAs and timestamps
No input schema was published for this tool.
argo__get_resource_treeFull owned resource tree for an appFull owned resource tree for an app
No input schema was published for this tool.
argo__sync_appTrigger sync — supports dry-run, prune, forceTrigger sync — supports dry-run, prune, force
No input schema was published for this tool.
argo__rollback_appRoll back to a specific history revision (dry-run by default)Roll back to a specific history revision (dry-run by default)
No input schema was published for this tool.
argo__terminate_opCancel an in-progress sync operation (dry-run by default)Cancel an in-progress sync operation (dry-run by default)
No input schema was published for this tool.
devops__debug_serviceCross-provider incident debugging: aggregates Kubernetes, ArgoCD, Prometheus, and PagerDuty data to diagnose service issuesCross-provider incident debugging: aggregates Kubernetes, ArgoCD, Prometheus, and PagerDuty data to diagnose service issues
No input schema was published for this tool.
devops__explain_changeExplain what changed: combines ArgoCD history, Kubernetes rollout history, and Prometheus anomaly window to identify the cause of issuesExplain what changed: combines ArgoCD history, Kubernetes rollout history, and Prometheus anomaly window to identify the cause of issues
No input schema was published for this tool.
devops__runbookSymptom-based diagnostic runbook: runs targeted checks across providers for a specific issue typeSymptom-based diagnostic runbook: runs targeted checks across providers for a specific issue type
No input schema was published for this tool.
devops__health_reportCross-provider health report: gathers status from all configured providers and returns an overall health assessmentCross-provider health report: gathers status from all configured providers and returns an overall health assessment
No input schema was published for this tool.
devops__incident_timelineIncident timeline: aggregates events from all providers into a chronological timeline for a serviceIncident timeline: aggregates events from all providers into a chronological timeline for a service
No input schema was published for this tool.
helm__list_releasesList Helm releases with status, chart, app versionList Helm releases with status, chart, app version
No input schema was published for this tool.
helm__get_statusGet status of a Helm releaseGet status of a Helm release
No input schema was published for this tool.
helm__get_valuesGet values of a Helm release (user-supplied or all)Get values of a Helm release (user-supplied or all)
No input schema was published for this tool.
helm__get_historyGet revision history of a Helm releaseGet revision history of a Helm release
No input schema was published for this tool.
helm__rollbackRollback a Helm release to a previous revision (mutate tier, dry_run by default)Rollback a Helm release to a previous revision (mutate tier, dry_run by default)
No input schema was published for this tool.
k8s__list_podsList pods with status, restarts, node, and ageList pods with status, restarts, node, and age
No input schema was published for this tool.
k8s__get_pod_logsGet logs from a pod containerGet logs from a pod container
No input schema was published for this tool.
k8s__describe_resourceFull describe for any resource typeFull describe for any resource type
No input schema was published for this tool.
k8s__get_eventsCluster or namespace events, filterable by reasonCluster or namespace events, filterable by reason
No input schema was published for this tool.
k8s__list_deploymentsDeployments with replica counts and rollout healthDeployments with replica counts and rollout health
No input schema was published for this tool.
k8s__get_resource_usageCPU/mem usage per pod via metrics-serverCPU/mem usage per pod via metrics-server
No input schema was published for this tool.
k8s__list_contextsAll kubeconfig contexts and the active oneAll kubeconfig contexts and the active one
No input schema was published for this tool.
k8s__switch_contextPreview context selection; set K8S_CONTEXT and restart to apply safelyPreview context selection; set K8S_CONTEXT and restart to apply safely
No input schema was published for this tool.
k8s__scale_deploymentScale replicas with dry-run diff previewScale replicas with dry-run diff preview
No input schema was published for this tool.
k8s__rollout_restartTrigger rolling restart of a deploymentTrigger rolling restart of a deployment
No input schema was published for this tool.
k8s__apply_manifestApply a manifest string with server-side dry-runApply a manifest string with server-side dry-run
No input schema was published for this tool.
k8s__delete_resourceprivilegedDelete a named resource — requires confirm: true or interactive confirmationDelete a named resource — requires confirm: true or interactive confirmation
No input schema was published for this tool.
k8s__get_node_statusGet node status with conditions, capacity, allocatable, labels, and taintsGet node status with conditions, capacity, allocatable, labels, and taints
No input schema was published for this tool.
k8s__get_network_policiesList network policies with podSelector, ingress/egress rulesList network policies with podSelector, ingress/egress rules
No input schema was published for this tool.
k8s__get_ingressesList ingresses with hosts, paths, backends, and TLS configList ingresses with hosts, paths, backends, and TLS config
No input schema was published for this tool.
k8s__diff_resourceCompare current resource state against last-applied-configuration annotation to show driftCompare current resource state against last-applied-configuration annotation to show drift
No input schema was published for this tool.
k8s__list_cronjobsList cronjobs with schedule, suspend status, active jobs, and last run timesList cronjobs with schedule, suspend status, active jobs, and last run times
No input schema was published for this tool.
k8s__get_cronjob_statusDetailed status of a specific cronjob including recent job historyDetailed status of a specific cronjob including recent job history
No input schema was published for this tool.
k8s__list_servicesList services with type, clusterIP, ports, selector, and externalIPsList services with type, clusterIP, ports, selector, and externalIPs
No input schema was published for this tool.
k8s__list_pvcsList PersistentVolumeClaims with status, capacity, accessModes, and storageClassList PersistentVolumeClaims with status, capacity, accessModes, and storageClass
No input schema was published for this tool.
k8s__get_hpaGet HorizontalPodAutoscaler details with metrics, replicas, and conditionsGet HorizontalPodAutoscaler details with metrics, replicas, and conditions
No input schema was published for this tool.
logs__get_recent_errorsGet recent error logs from Loki for debugging incidentsGet recent error logs from Loki for debugging incidents
No input schema was published for this tool.
40 of 40 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
77 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+65 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies, optionalDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.