@notharshhaa/devops-mcp

MCPcommunity
v2.1.1DevOps MCP ContributorsMITUpdated 6d agonpmGitHub

Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.

Works in
ClaudeCursorCopilotGemini

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.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
285Downloads/wk
4GitHub stars
1Forks
6d agoLast update
Reads these credentials
  • ARGOCD_TOKENAPI keyoptional

    ArgoCD authentication token

  • PROMETHEUS_BEARER_TOKENAPI keyoptional

    Prometheus bearer token

  • PAGERDUTY_TOKENAPI keyoptional

    PagerDuty API token

  • LOKI_TOKENAPI keyoptional

    Loki 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.

Package
AuthorDevOps MCP Contributors
LicenseMIT
Version2.1.1
Sourcenpm+mcp-registry
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface40 tools · 1 privileged
Security scan✓ Cleanv2.1.1 · todayHow well does this scan work?
EvalsNone
IndexedOct 10, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

40 tools · 1 privileged
Statically extracted from the published packagev2.1.1 · 15h ago

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 repo

All apps with health, sync status, source repo

No input schema was published for this tool.

argo__get_appFull spec and status for one application

Full spec and status for one application

No input schema was published for this tool.

argo__get_app_diffLive diff between git and cluster state

Live diff between git and cluster state

No input schema was published for this tool.

argo__get_app_historyDeployment history with git SHAs and timestamps

Deployment history with git SHAs and timestamps

No input schema was published for this tool.

argo__get_resource_treeFull owned resource tree for an app

Full owned resource tree for an app

No input schema was published for this tool.

argo__sync_appTrigger sync — supports dry-run, prune, force

Trigger 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 issues

Cross-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 issues

Explain 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 type

Symptom-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 assessment

Cross-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 service

Incident 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 version

List Helm releases with status, chart, app version

No input schema was published for this tool.

helm__get_statusGet status of a Helm release

Get 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 release

Get 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 age

List pods with status, restarts, node, and age

No input schema was published for this tool.

k8s__get_pod_logsGet logs from a pod container

Get logs from a pod container

No input schema was published for this tool.

k8s__describe_resourceFull describe for any resource type

Full describe for any resource type

No input schema was published for this tool.

k8s__get_eventsCluster or namespace events, filterable by reason

Cluster or namespace events, filterable by reason

No input schema was published for this tool.

k8s__list_deploymentsDeployments with replica counts and rollout health

Deployments with replica counts and rollout health

No input schema was published for this tool.

k8s__get_resource_usageCPU/mem usage per pod via metrics-server

CPU/mem usage per pod via metrics-server

No input schema was published for this tool.

k8s__list_contextsAll kubeconfig contexts and the active one

All 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 safely

Preview 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 preview

Scale replicas with dry-run diff preview

No input schema was published for this tool.

k8s__rollout_restartTrigger rolling restart of a deployment

Trigger rolling restart of a deployment

No input schema was published for this tool.

k8s__apply_manifestApply a manifest string with server-side dry-run

Apply 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 confirmation

Delete 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 taints

Get 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 rules

List 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 config

List 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 drift

Compare 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 times

List 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 history

Detailed 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 externalIPs

List 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 storageClass

List PersistentVolumeClaims with status, capacity, accessModes, and storageClass

No input schema was published for this tool.

k8s__get_hpaGet HorizontalPodAutoscaler details with metrics, replicas, and conditions

Get 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 incidents

Get 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.

About

Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.

Keywords
mcpmodel-context-protocolkubernetesargocdprometheuspagerdutydevopsclaude
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-10 — observed resolution, not a publisher declaration.

60 packages resolved · 7 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

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)

Declared but not resolved

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.

Topics

Related in monitoring & logging