# @notharshhaa/devops-mcp Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 2.1.1 - **Author:** DevOps MCP Contributors - **License:** MIT - **npm:** @notharshhaa/devops-mcp - **Source:** https://github.com/NotHarshhaa/devops-mcp - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 0 days ## Security scan - **Status:** clean - **Scanned:** 2026-10-10T22:28:10.361Z - **Version scanned:** 2.1.1 - **CVEs:** none found by OSV at scan time ## Tools 40 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `argo__list_apps` — All apps with health, sync status, source repo - `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__sync_app` — Trigger sync — supports dry-run, prune, force - `argo__rollback_app` — Roll back to a specific history revision (dry-run by default) - `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__runbook` — Symptom-based diagnostic runbook: runs targeted checks across providers for a specific issue type - `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 - `helm__list_releases` — List Helm releases with status, chart, app version - `helm__get_status` — Get status of a Helm release - `helm__get_values` — Get values of a Helm release (user-supplied or all) - `helm__get_history` — Get revision history of a Helm release - `helm__rollback` — Rollback a Helm release to a previous revision (mutate tier, dry_run by default) - `k8s__list_pods` — List pods with status, restarts, node, and age - `k8s__get_pod_logs` — Get logs from a pod container - `k8s__describe_resource` — Full describe for any resource type - `k8s__get_events` — Cluster or namespace events, filterable by reason - `k8s__list_deployments` — Deployments with replica counts and rollout health - `k8s__get_resource_usage` — CPU/mem usage per pod via metrics-server - `k8s__list_contexts` — All kubeconfig contexts and the active one - `k8s__switch_context` — Preview context selection; set K8S_CONTEXT and restart to apply safely - `k8s__scale_deployment` — Scale replicas with dry-run diff preview - `k8s__rollout_restart` — Trigger rolling restart of a deployment - `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__get_node_status` — Get node status with conditions, capacity, allocatable, labels, and taints - `k8s__get_network_policies` — List network policies with podSelector, ingress/egress rules - `k8s__get_ingresses` — List ingresses with hosts, paths, backends, and TLS config - `k8s__diff_resource` — Compare current resource state against last-applied-configuration annotation to show drift - `k8s__list_cronjobs` — List cronjobs with schedule, suspend status, active jobs, and last run times - `k8s__get_cronjob_status` — Detailed status of a specific cronjob including recent job history - `k8s__list_services` — List services with type, clusterIP, ports, selector, and externalIPs - `k8s__list_pvcs` — List PersistentVolumeClaims with status, capacity, accessModes, and storageClass - `k8s__get_hpa` — Get HorizontalPodAutoscaler details with metrics, replicas, and conditions - `logs__get_recent_errors` — Get recent error logs from Loki for debugging incidents ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"devops\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"@notharshhaa/devops-mcp\"\n ],\n \"env\": {\n \"ARGOCD_TOKEN\": \"\",\n \"PROMETHEUS_BEARER_TOKEN\": \"\",\n \"PAGERDUTY_TOKEN\": \"\",\n \"LOKI_TOKEN\": \"\"\n }\n }\n }\n}" ``` **Credentials it will ask for** (names only — Forge never holds a value): - `ARGOCD_TOKEN` — Argocd Token (optional) - `PROMETHEUS_BEARER_TOKEN` — Prometheus Bearer Token (optional) - `PAGERDUTY_TOKEN` — Pagerduty Token (optional) - `LOKI_TOKEN` — Loki Token (optional) Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one. - This entry needs 4 credentials (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset. ## Blast radius Extensive blast radius — deletes data; holds an api key. - Floor 55, ceiling 55 (tier: extensive) - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/%40notharshhaa%2Fdevops-mcp - Install plan: https://forgeregistry.com/api/v1/packages/%40notharshhaa%2Fdevops-mcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/%40notharshhaa%2Fdevops-mcp - HTML page: https://forgeregistry.com/registry/%40notharshhaa%2Fdevops-mcp - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.