Devops Mcp
A unified DevOps command center that wires Claude directly into your production infrastructure. Bundles six providers under one MCP server: query pods and deployments via Kubernetes client-go, inspect ArgoCD sync diffs and rollback history, run PromQL queries and check firing alerts, pull PagerDuty incidents and on-call schedules, search Loki logs with LogQL, and manage Helm releases. Ships read-only tools for safe exploration (pod logs, resource usage, event streams) plus mutation and destructive tiers with dry-run and confirmation gates. Configured entirely through environment variables, so you can enable only the providers you actually use. Install with npx, point it at your kubeconfig and API tokens, then ask Claude to debug CrashLoopBackOffs or correlate metrics across your entire stack without leaving the chat.
- GitHub stars
- 4
- tools
- 60
- auth
- Secret needed
- transport
- STDIO
- env vars
- 10
- last updated
- Oct 5, 2026
Tools
60 toolsPublic tool metadata for what this MCP can expose to an agent.
k8s__list_podsList pods with status, restarts, node, age
List pods with status, restarts, node, age
No parameter schema in public metadata yet.
k8s__get_pod_logsTail or stream logs from a pod container
Tail or stream logs from a pod container
No parameter schema in public metadata yet.
k8s__describe_resourceFull describe for any resource type (pod, service, configmap, secret [values auto-redacted], deployment, statefulset, daemonset, job, cronjob)
Full describe for any resource type (pod, service, configmap, secret [values auto-redacted], deployment, statefulset, daemonset, job, cronjob)
No parameter schema in public metadata yet.
k8s__get_eventsCluster or namespace events, filterable by reason
Cluster or namespace events, filterable by reason
No parameter schema in public metadata yet.
k8s__list_deploymentsDeployments with replica counts, rollout health, and container images
Deployments with replica counts, rollout health, and container images
No parameter schema in public metadata yet.
k8s__get_resource_usageCPU/mem usage per pod via metrics-server
CPU/mem usage per pod via metrics-server
No parameter schema in public metadata yet.
k8s__get_node_statusNode health, conditions, capacity, allocatable resources, taints
Node health, conditions, capacity, allocatable resources, taints
No parameter schema in public metadata yet.
k8s__get_network_policiesNetwork policies with pod selectors and ingress/egress rules
Network policies with pod selectors and ingress/egress rules
No parameter schema in public metadata yet.
k8s__get_ingressesIngress resources with hosts, paths, backends, TLS config
Ingress resources with hosts, paths, backends, TLS config
No parameter schema in public metadata yet.
k8s__list_cronjobsCronJobs with schedule, last run, active jobs, suspend status
CronJobs with schedule, last run, active jobs, suspend status
No parameter schema in public metadata yet.
k8s__get_cronjob_statusDetailed CronJob status with recent job history
Detailed CronJob status with recent job history
No parameter schema in public metadata yet.
k8s__diff_resourceCompare current resource state vs last-applied-configuration
Compare current resource state vs last-applied-configuration
No parameter schema in public metadata yet.
k8s__get_hpaHorizontalPodAutoscaler with current/target metrics and scaling status
HorizontalPodAutoscaler with current/target metrics and scaling status
No parameter schema in public metadata yet.
k8s__list_pvcsPersistentVolumeClaims with status, capacity, storage class
PersistentVolumeClaims with status, capacity, storage class
No parameter schema in public metadata yet.
k8s__list_servicesServices with type, ports, selectors, clusterIP, endpoints
Services with type, ports, selectors, clusterIP, endpoints
No parameter schema in public metadata yet.
k8s__list_contextsAll kubeconfig contexts and the active one
All kubeconfig contexts and the active one
No parameter schema in public metadata yet.
k8s__switch_contextPreview a context selection; set K8S_CONTEXT and restart to apply it safely
Preview a context selection; set K8S_CONTEXT and restart to apply it safely
No parameter schema in public metadata yet.
k8s__scale_deploymentScale replicas with dry-run diff preview
Scale replicas with dry-run diff preview
No parameter schema in public metadata yet.
k8s__apply_manifestApply a manifest string with server-side dry-run
Apply a manifest string with server-side dry-run
No parameter schema in public metadata yet.
k8s__rollout_restartTrigger rolling restart of a deployment or statefulset
Trigger rolling restart of a deployment or statefulset
No parameter schema in public metadata yet.
k8s__delete_resourceDelete a named resource (pod, service, configmap, secret, deployment, statefulset, daemonset, job, cronjob) — requires direct or interactive confirmation
Delete a named resource (pod, service, configmap, secret, deployment, statefulset, daemonset, job, cronjob) — requires direct or interactive confirmation
No parameter schema in public metadata yet.
argo__list_appsAll apps with health, sync status, source repo
All apps with health, sync status, source repo
No parameter schema in public metadata yet.
argo__get_appFull spec and status for one application
Full spec and status for one application
No parameter schema in public metadata yet.
argo__get_app_diffLive diff between git and cluster state
Live diff between git and cluster state
No parameter schema in public metadata yet.
argo__get_app_historyDeployment history with git SHAs and timestamps
Deployment history with git SHAs and timestamps
No parameter schema in public metadata yet.
argo__get_resource_treeFull owned resource tree for an app
Full owned resource tree for an app
No parameter schema in public metadata yet.
argo__sync_appTrigger sync — supports dry-run, prune, force
Trigger sync — supports dry-run, prune, force
No parameter schema in public metadata yet.
argo__rollback_appPreview rollback to a history revision; set dry_run: false to execute
Preview rollback to a history revision; set dry_run: false to execute
No parameter schema in public metadata yet.
argo__terminate_opPreview cancellation of an in-progress sync; set dry_run: false to execute
Preview cancellation of an in-progress sync; set dry_run: false to execute
No parameter schema in public metadata yet.
prom__queryInstant PromQL query with label + value output
Instant PromQL query with label + value output
No parameter schema in public metadata yet.
prom__query_rangeRange query with step, returns time-series data
Range query with step, returns time-series data
No parameter schema in public metadata yet.
prom__list_alertsAll alert rules with state (firing / pending / inactive)
All alert rules with state (firing / pending / inactive)
No parameter schema in public metadata yet.
prom__get_firing_alertsOnly currently firing alerts with duration
Only currently firing alerts with duration
No parameter schema in public metadata yet.
prom__list_targetsAll scrape targets with health and last scrape
All scrape targets with health and last scrape
No parameter schema in public metadata yet.
prom__label_valuesEnumerate values for a given label name
Enumerate values for a given label name
No parameter schema in public metadata yet.
prom__metric_metadataType, help text, and unit for a metric
Type, help text, and unit for a metric
No parameter schema in public metadata yet.
prom__compare_periodsCompare metrics between two time windows — detect before/after deployment changes
Compare metrics between two time windows — detect before/after deployment changes
No parameter schema in public metadata yet.
prom__slo_statusSLO compliance — error budget remaining, burn rate, time to exhaustion
SLO compliance — error budget remaining, burn rate, time to exhaustion
No parameter schema in public metadata yet.
prom__summarize_service_healthSmart summary - human-readable service health metrics including latency changes, error rate vs SLO, and traffic patterns
Smart summary - human-readable service health metrics including latency changes, error rate vs SLO, and traffic patterns
No parameter schema in public metadata yet.
logs__get_recent_errorsGet recent error logs from Loki for debugging incidents
Get recent error logs from Loki for debugging incidents
No parameter schema in public metadata yet.
logs__searchSearch logs in Loki with custom query for root cause analysis
Search logs in Loki with custom query for root cause analysis
No parameter schema in public metadata yet.
pd__list_incidentsOpen incidents with severity, status, assignee
Open incidents with severity, status, assignee
No parameter schema in public metadata yet.
pd__get_incidentFull detail with alerts, notes, timeline
Full detail with alerts, notes, timeline
No parameter schema in public metadata yet.
pd__who_is_oncallCurrent on-call per schedule or escalation policy
Current on-call per schedule or escalation policy
No parameter schema in public metadata yet.
pd__list_servicesAll services with integration keys and status
All services with integration keys and status
No parameter schema in public metadata yet.
pd__get_log_entriesAudit log for an incident (all state changes)
Audit log for an incident (all state changes)
No parameter schema in public metadata yet.
pd__acknowledge_incidentPreview acknowledgement; set dry_run: false to execute
Preview acknowledgement; set dry_run: false to execute
No parameter schema in public metadata yet.
pd__add_notePreview appending a note; set dry_run: false to execute
Preview appending a note; set dry_run: false to execute
No parameter schema in public metadata yet.
pd__escalate_incidentEscalate to a different policy — requires direct or interactive confirmation
Escalate to a different policy — requires direct or interactive confirmation
No parameter schema in public metadata yet.
pd__summarize_incidentIncident auto-summary - what happened, affected services, probable root cause, current status
Incident auto-summary - what happened, affected services, probable root cause, current status
No parameter schema in public metadata yet.
helm__list_releasesList Helm releases with status, chart, app version
List Helm releases with status, chart, app version
No parameter schema in public metadata yet.
helm__get_statusFull status of a Helm release
Full status of a Helm release
No parameter schema in public metadata yet.
helm__get_valuesUser-supplied or computed values for a release
User-supplied or computed values for a release
No parameter schema in public metadata yet.
helm__get_historyRevision history of a release
Revision history of a release
No parameter schema in public metadata yet.
helm__rollbackRollback to a previous revision (dry-run by default)
Rollback to a previous revision (dry-run by default)
No parameter schema in public metadata yet.
devops__debug_serviceCross-provider incident debugging - aggregates Kubernetes, ArgoCD, Prometheus, and PagerDuty data to diagnose service issues in one command
Cross-provider incident debugging - aggregates Kubernetes, ArgoCD, Prometheus, and PagerDuty data to diagnose service issues in one command
No parameter schema in public metadata yet.
devops__explain_changeExplain what changed - combines ArgoCD history, Kubernetes rollout history, and Prometheus anomaly window to identify cause of issues
Explain what changed - combines ArgoCD history, Kubernetes rollout history, and Prometheus anomaly window to identify cause of issues
No parameter schema in public metadata yet.
devops__runbookAutomated runbook - symptom-based diagnostic that runs targeted checks (crashloop, high-latency, oom, 5xx, pod-pending)
Automated runbook - symptom-based diagnostic that runs targeted checks (crashloop, high-latency, oom, 5xx, pod-pending)
No parameter schema in public metadata yet.
devops__health_reportCluster health report - one-shot assessment across all providers with overall status (healthy/degraded/critical)
Cluster health report - one-shot assessment across all providers with overall status (healthy/degraded/critical)
No parameter schema in public metadata yet.
devops__incident_timelineIncident timeline - unified event timeline across K8s, ArgoCD, Prometheus, and PagerDuty sorted chronologically
Incident timeline - unified event timeline across K8s, ArgoCD, Prometheus, and PagerDuty sorted chronologically
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
KUBECONFIGPath to Kubernetes kubeconfig file
K8S_CONTEXTKubernetes context to use
ARGOCD_SERVERArgoCD server URL
ARGOCD_TOKENsecretArgoCD authentication token
PROMETHEUS_URLPrometheus server URL
PROMETHEUS_BEARER_TOKENsecretPrometheus bearer token
PAGERDUTY_TOKENsecretPagerDuty API token
PAGERDUTY_USER_EMAILPagerDuty user email for mutations requiring From header
LOKI_URLLoki server URL
LOKI_TOKENsecretLoki authentication token
Readme
devops-mcp
Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.
What is this?
devops-mcp is an open source Model Context Protocol server that gives AI agents (Claude, etc.) real-time read and write access to your infrastructure stack — all from a single install.
Instead of copy-pasting kubectl output into a chat window, you can ask:
"Why is the payments deployment in CrashLoopBackOff?" "What changed in the last ArgoCD sync for the auth app?" "Show me the p99 latency for the API gateway over the last hour." "Who's on call right now and what incidents are open?" "Debug the payments service - what's wrong with it?"
...and get live answers, sourced directly from your cluster and tooling.
Providers included:
Details
- Repository
- github.com/notharshhaa/devops-mcp
- Categories
- Cloud & Infrastructure, Monitoring & Observability
- Package
@notharshhaa/devops-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
More from notharshhaa
Related Cloud & Infrastructure MCP servers
View all
Cyntrisec CLI (Historical)cyntrisec/cyntrisec-cliHistorical AWS analysis CLI; not a current Cyntrisec product.3stars
OCI Pricingjasonwilbur/oci-pricing-mcpOracle Cloud Infrastructure pricing data with cost calculators and comparisons3stars
Shortcut Mcpstayce/streamshortcut-cloudflareShortcut project management. Create, update, search stories and manage workflows.0stars
VMware AVIzw008/vmware-aviVMware AVI (NSX ALB) load balancer plus AKO Kubernetes ops — 29 MCP tools.2stars
K8scortex Mcpapatilgtn/k8scortex-mcpKubernetes MCP server: 75 tools for GKE, AKS, EKS, RBAC, audit logging, GitOps, multi-cluster.1stars
Deployment.iodeployment-io/cursor-pluginDeploy apps on your cloud. Create environments, configure infrastructure, and monitor jobs.0stars