Skip to content
Agentmart
Submit a tool

DevOps MCP

Unified MCP server for Kubernetes, ArgoCD, Prometheus, PagerDuty, and Loki

Connector by NotHarshhaa · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 4
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/notharshhaa-devops-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Unified MCP server for Kubernetes, ArgoCD, Prometheus, PagerDuty, and Loki

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
44 read · 7 write · 4 delete · 5 not yet classified
Secrets
4 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Node.js package

Tools by what they do 60

Read from the source code; the running server may list different tools.

Read 44 · Look things up without changing anything.

  • argo__get_app
  • argo__get_app_diff
  • argo__get_app_history
  • argo__get_resource_tree
  • argo__list_apps
  • devops__explain_change
  • devops__health_report
  • helm__get_history
  • helm__get_status
  • helm__get_values
  • helm__list_releases
  • k8s__describe_resource
Show 32 more tools
  • k8s__diff_resource
  • k8s__get_cronjob_status
  • k8s__get_events
  • k8s__get_hpa
  • k8s__get_ingresses
  • k8s__get_network_policies
  • k8s__get_node_status
  • k8s__get_pod_logs
  • k8s__get_resource_usage
  • k8s__list_contexts
  • k8s__list_cronjobs
  • k8s__list_deployments
  • k8s__list_pods
  • k8s__list_pvcs
  • k8s__list_services
  • k8s__switch_context
  • logs__get_recent_errors
  • logs__search
  • pd__get_incident
  • pd__get_log_entries
  • pd__list_incidents
  • pd__list_services
  • pd__summarize_incident
  • pd__who_is_oncall
  • prom__compare_periods
  • prom__get_firing_alerts
  • prom__list_alerts
  • prom__list_targets
  • prom__query
  • prom__query_range
  • prom__slo_status
  • prom__summarize_service_health

Write 7 · Create, change, send or run things.

  • argo__sync_app
  • k8s__apply_manifest
  • k8s__rollout_restart
  • k8s__scale_deployment
  • pd__add_note
  • prom__label_values
  • prom__metric_metadata

Delete 4 · Delete, drop, revoke or wipe things.

  • argo__rollback_app
  • argo__terminate_op
  • helm__rollback
  • k8s__delete_resource

Not yet classified 5 · We could not tell from the name and description.

  • devops__debug_service
  • devops__incident_timeline
  • devops__runbook
  • pd__acknowledge_incident
  • pd__escalate_incident

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • ARGOCD_TOKEN
  • LOKI_TOKEN
  • PAGERDUTY_TOKEN
  • PROMETHEUS_BEARER_TOKEN

Other settings (environment variables or headers).

  • ARGOCD_SERVER
  • K8S_CONTEXT
  • KUBECONFIG
  • LOKI_URL
  • PAGERDUTY_USER_EMAIL
  • PROMETHEUS_URL

Network hosts it talks to 1

  • api.pagerduty.com · found in code

Tools (60)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • argo__get_app

    Full spec and status for one application

  • argo__get_app_diff

    Live diff between git and cluster state

  • argo__get_app_history

    Deployment history with git SHAs and timestamps

  • argo__get_resource_tree

    Full owned resource tree for an app

  • argo__list_apps

    All apps with health, sync status, source repo

  • argo__rollback_app

    Roll back to a specific history revision (dry-run by default)

  • argo__sync_app

    Trigger sync — supports dry-run, prune, force

  • argo__terminate_op

    Cancel an in-progress sync operation (dry-run by default)

  • devops__debug_service

    Cross-provider incident debugging: aggregates Kubernetes, ArgoCD, Prometheus, and PagerDuty data to diagnose service issues

  • devops__explain_change

    Explain what changed: combines ArgoCD history, Kubernetes rollout history, and Prometheus anomaly window to identify the cause of issues

  • devops__health_report

    Cross-provider health report: gathers status from all configured providers and returns an overall health assessment

  • devops__incident_timeline

    Incident timeline: aggregates events from all providers into a chronological timeline for a service

  • devops__runbook

    Symptom-based diagnostic runbook: runs targeted checks across providers for a specific issue type

  • helm__get_history

    Get revision history of a Helm release

  • helm__get_status

    Get status of a Helm release

Show 45 more tools
  • helm__get_values

    Get values of a Helm release (user-supplied or all)

  • helm__list_releases

    List Helm releases with status, chart, app version

  • helm__rollback

    Rollback a Helm release to a previous revision (mutate tier, dry_run by default)

  • k8s__apply_manifest

    Apply a manifest string with server-side dry-run

  • k8s__delete_resource

    Delete a named resource — requires confirm: true or interactive confirmation

  • k8s__describe_resource

    Full describe for any resource type

  • k8s__diff_resource

    Compare current resource state against last-applied-configuration annotation to show drift

  • k8s__get_cronjob_status

    Detailed status of a specific cronjob including recent job history

  • k8s__get_events

    Cluster or namespace events, filterable by reason

  • k8s__get_hpa

    Get HorizontalPodAutoscaler details with metrics, replicas, and conditions

  • k8s__get_ingresses

    List ingresses with hosts, paths, backends, and TLS config

  • k8s__get_network_policies

    List network policies with podSelector, ingress/egress rules

  • k8s__get_node_status

    Get node status with conditions, capacity, allocatable, labels, and taints

  • k8s__get_pod_logs

    Get logs from a pod container

  • k8s__get_resource_usage

    CPU/mem usage per pod via metrics-server

  • k8s__list_contexts

    All kubeconfig contexts and the active one

  • k8s__list_cronjobs

    List cronjobs with schedule, suspend status, active jobs, and last run times

  • k8s__list_deployments

    Deployments with replica counts and rollout health

  • k8s__list_pods

    List pods with status, restarts, node, and age

  • k8s__list_pvcs

    List PersistentVolumeClaims with status, capacity, accessModes, and storageClass

  • k8s__list_services

    List services with type, clusterIP, ports, selector, and externalIPs

  • k8s__rollout_restart

    Trigger rolling restart of a deployment

  • k8s__scale_deployment

    Scale replicas with dry-run diff preview

  • k8s__switch_context

    Preview context selection; set K8S_CONTEXT and restart to apply safely

  • logs__get_recent_errors

    Get recent error logs from Loki for debugging incidents

  • logs__search

    Search logs in Loki with custom query for root cause analysis

  • pd__acknowledge_incident

    Acknowledge an incident (dry-run by default)

  • pd__add_note

    Append a note to an incident timeline (dry-run by default)

  • pd__escalate_incident

    Escalate to a different policy — requires confirm: true or interactive confirmation

  • pd__get_incident

    Full detail with alerts, notes, timeline

  • pd__get_log_entries

    Audit log for an incident (all state changes)

  • pd__list_incidents

    Open incidents with severity, status, assignee

  • pd__list_services

    All services with integration keys and status

  • pd__summarize_incident

    🚨 Incident auto-summary - what happened, affected services, probable root cause, current status

  • pd__who_is_oncall

    Current on-call per schedule or escalation policy

  • prom__compare_periods

    Compare a metric between two time windows to detect before/after changes

  • prom__get_firing_alerts

    Only currently firing alerts with duration

  • prom__label_values

    Enumerate values for a given label name

  • prom__list_alerts

    All alert rules with state (firing / pending / inactive)

  • prom__list_targets

    All scrape targets with health and last scrape

  • prom__metric_metadata

    Type, help text, and unit for a metric

  • prom__query

    Instant PromQL query with label + value output

  • prom__query_range

    Range query with step, returns time-series data

  • prom__slo_status

    SLO status for a service: current SLI, error budget consumption, burn rate, and time to exhaustion

  • prom__summarize_service_health

    Smart Prometheus summary: human-readable service health metrics including latency changes, error rate vs SLO, and traffic patterns

Signals

Stars
4
Forks
1
Open issues
0
Weekly downloads
43
Last commit
Oct 5, 2026 (25 days ago)
Last release
Oct 5, 2026 (25 days ago)
Last package publish
Oct 5, 2026 (25 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.NotHarshhaa/devops-mcp
Version
2.1.1
Auth
API key
Packages
npm @notharshhaa/devops-mcp
License
MIT
Repository
github.com/NotHarshhaa/devops-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from NotHarshhaa

Cite this page

DevOps MCP. Agent Mart. https://agentmart.dev/connectors/notharshhaa-devops-mcp (last updated 2026-10-24)