kubernetes-mcp-server
A Model Context Protocol (MCP) server for Kubernetes and OpenShift
What can you do with kubernetes-mcp-server?
- configuration_contexts_list — List all available context names and associated server urls from the kubeconfig file
- targets_list — List all available targets
- configuration_view — Get the current Kubernetes configuration content as a kubeconfig YAML
- events_list — List Kubernetes events (warnings, errors, state changes) for debugging and troubleshooting in the current cluster from all namespaces. Use limit and continue to retrieve a large list one page at a time.
- namespaces_list — List all the Kubernetes namespaces in the current cluster. Use limit and continue to retrieve a large list one page at a time.
- projects_list — List all the OpenShift projects in the current cluster. Use limit and continue to retrieve a large list one page at a time.
Tool descriptions from the project's README, checked 16 Nov 2026.
About kubernetes-mcp-server
✨ Features | 🚀 Getting Started | 🎥 Demos | ⚙️ Configuration | 🛠️ Tools | 💬 Community | 🧑💻 Development https://github.com/user-attachments/assets/be2b67b3-fc1c-4d11-ae46-93deba8ed98e
Opening text of the project's README, checked 16 Nov 2026.
Install
{
"mcpServers": {
"kubernetes": {
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server"
]
}
}
}Config as documented in its source, checked 16 Nov 2026. Placeholders such as API keys are the project's own: replace them with your values.
Requirements listed
- Access to a Kubernetes cluster.
Setup documented for
Tools (78)
| configuration_contexts_list | List all available context names and associated server urls from the kubeconfig file |
| targets_list | List all available targets |
| configuration_view | Get the current Kubernetes configuration content as a kubeconfig YAML |
| events_list | List Kubernetes events (warnings, errors, state changes) for debugging and troubleshooting in the current cluster from all namespaces. Use limit and continue to retrieve a large list one page at a time. |
| namespaces_list | List all the Kubernetes namespaces in the current cluster. Use limit and continue to retrieve a large list one page at a time. |
| projects_list | List all the OpenShift projects in the current cluster. Use limit and continue to retrieve a large list one page at a time. |
| nodes_log | Get logs from a Kubernetes node (kubelet, kube-proxy, or other system logs). This accesses node logs through the Kubernetes API proxy to the kubelet |
| nodes_stats_summary | |
| nodes_top | List the resource consumption (CPU and memory) as recorded by the Kubernetes Metrics Server for the specified Kubernetes Nodes or all nodes in the cluster. Use limit and continue to retrieve a large list one page at a time. |
| pods_list | List all the Kubernetes pods in the current cluster from all namespaces. Use limit and continue to retrieve a large list one page at a time. |
| pods_list_in_namespace | List all the Kubernetes pods in the specified namespace in the current cluster. Use limit and continue to retrieve a large list one page at a time. |
| pods_get | Get a Kubernetes Pod in the current or provided namespace with the provided name |
| pods_delete | Delete a Kubernetes Pod in the current or provided namespace with the provided name |
| pods_top | |
| pods_exec | Execute a command in a Kubernetes Pod (shell access, run commands in container) in the current or provided namespace with the provided name and command |
| pods_log | Get the logs of a Kubernetes Pod in the current or provided namespace with the provided name |
| pods_run | Run a Kubernetes Pod in the current or provided namespace with the provided container image and optional name |
| resources_list | List Kubernetes resources and objects in the current cluster by providing their apiVersion and kind and optionally the namespace and label selector. Use limit and continue to retrieve a large list one page at a time. |
| resources_get | Get a Kubernetes resource in the current cluster by providing its apiVersion, kind, optionally the namespace, and its name |
| resources_create_or_update | |
| resources_delete | Delete a Kubernetes resource in the current cluster by providing its apiVersion, kind, optionally the namespace, and its name |
| resources_scale | |
| api_resources_list | |
| helm_install | Install (deploy) a Helm chart to create a release in the current or provided namespace |
| helm_list | |
| helm_uninstall | Uninstall a Helm release in the current or provided namespace |
| kcp_workspaces_list | List all available kcp workspaces in the current cluster |
| kcp_workspace_describe | Get detailed information about a specific kcp workspace |
| kiali_get_mesh_traffic_graph | Returns service-to-service traffic topology, dependencies, and network metrics (throughput, response time, mTLS) for the specified namespaces. Use this to diagnose routing issues, latency, or find upstream/downstream dependencies. |
| kiali_get_mesh_status | |
| kiali_manage_istio_config_read | |
| kiali_manage_istio_config | |
| kiali_list_mesh_clusters | |
| kiali_get_resource_details | Fetches a list of resources OR retrieves detailed data for a specific resource. If 'resourceName' is omitted, it returns a list. If 'resourceName' is provided, it returns details for that specific resource. |
| kiali_list_traces | |
| kiali_get_trace_details | Fetches a single distributed trace by traceid and returns its call hierarchy (service tree with duration, status, and nested calls). Use this after listtraces to drill into a specific trace. |
| kiali_get_pod_performance | Returns a human-readable text summary with current Pod CPU/memory usage (from Prometheus) compared to Kubernetes requests/limits (from the Pod spec). Useful to answer questions like 'Is this workload using too much memory?' |
| kiali_get_logs | |
| kiali_get_metrics | Returns a compact JSON summary of Istio metrics (latency quantiles, traffic trends, throughput, payload sizes) for the given resource. |
| vm_clone | Clone a VirtualMachine on KubeVirt by creating a VirtualMachineClone resource. This creates a copy of the source VM with a new name using the KubeVirt Clone API |
| vm_console_screenshot | |
| vm_create | |
| vm_guest_info | |
| vm_lifecycle | Manage KubeVirt VirtualMachine lifecycle: start, stop, restart, pause, or unpause a VM |
| vm_create_from_template | |
| vm_troubleshoot | |
| netobserv_list_flows | Lists NetObserv network flow records from Loki. Use when investigating traffic between workloads, IPs, ports, or protocols in a namespace or time window. |
| netobserv_export_flows | Exports NetObserv flow records as CSV with the same filters as list_flows. Use when the user needs downloadable flow data for audits or offline analysis. |
| netobserv_get_flow_metrics | Returns aggregated NetObserv flow metrics as topology or time-series data. Use for throughput, TLS/DNS/drop breakdowns, and namespace or workload traffic analysis; see aggregateBy and groups for grouping options. |
| loki_list_instances | List LokiStack instances available in the Kubernetes cluster. |
| loki_label_names | List available Loki label names for a time range. Use this before writing LogQL queries. |
| loki_label_values | List possible values for a Loki label key. Use this to build precise label matchers in LogQL. |
| loki_query_range | Execute a Loki LogQL range query and return matching log streams and lines. |
| list_metrics | MANDATORY FIRST STEP: List all available metric names in Prometheus. |
| execute_instant_query | Execute a PromQL instant query to get current/point-in-time values. |
| execute_range_query | Execute a PromQL range query to get time-series data over a period. |
| show_timeseries | Display the results as an interactive timeseries chart. |
| get_label_names | Get all label names (dimensions) available for filtering a metric. |
| get_label_values | Get all unique values for a specific label. |
| get_series | Get time series matching selectors and preview cardinality. |
| get_alerts | Get alerts from Alertmanager. |
| get_silences | Get silences from Alertmanager. |
| otelcol_list_components | List available OpenTelemetry Collector components (receivers, processors, exporters, extensions, connectors) for a given version. |
| otelcol_get_component_schema | Get the JSON schema for an OpenTelemetry Collector component's configuration options. |
| otelcol_validate_config | Validate an OpenTelemetry Collector component configuration against its JSON schema. |
| otelcol_get_versions | List available OpenTelemetry Collector versions and identify the latest. |
| tempo_list_instances | List all Tempo instances available in the Kubernetes cluster. |
| tempo_get_trace_by_id | Retrieve a single distributed trace by its trace ID from Tempo. |
| tempo_search_traces | Search for distributed traces in Tempo using TraceQL. |
| tempo_search_tags | List available tag names (attribute keys) in Tempo, grouped by scope. |
| tempo_search_tag_values | List the known values for a specific tag (attribute key) in Tempo. |
| tekton_pipeline_start | Start a Tekton Pipeline by creating a PipelineRun that references it |
| tekton_pipelinerun_lifecycle | Manage a Tekton PipelineRun lifecycle by restarting it with the same spec or cancelling it by setting spec.status to Cancelled. |
| tekton_pipelinerun_logs | Get logs for all TaskRuns owned by a Tekton PipelineRun. Use this to inspect PipelineRun execution output without locating pods manually. |
| tekton_pipelinerun_diagnose | |
| tekton_task_start | Start a Tekton Task by creating a TaskRun that references it |
| tekton_taskrun_restart | Restart a Tekton TaskRun by creating a new TaskRun with the same spec |
| tekton_taskrun_logs | Get the logs from a Tekton TaskRun by resolving its underlying pod |
Tool names from the README, checked 16 Nov 2026.
kubernetes-mcp-server compared with other Kubernetes servers
| Server | Licence | Tools | Last commit | Stars |
|---|---|---|---|---|
| kubernetes-mcp-server | Apache-2.0 | 78 | 14 Nov 2026 | 2,250 |
| mcp-server-kubernetes | MIT | 24 | 13 Nov 2026 | 1,612 |
Every value is a checked fact on that server's own page. This is a comparison of facts, not a ranking.
Verified facts
- Maintainer
- containers
Source · checked 16 Nov 2026
- Licence
- Apache-2.0
Source · checked 16 Nov 2026
- Transport
- stdio
- streamable-http
Source · checked 16 Nov 2026
- Setup documented for
- Claude Code
- Claude Desktop
- Cursor
- VS Code
- GitHub Copilot
Source · checked 16 Nov 2026
- Repository
- github.com/containers/kubernetes-mcp-server
Source · checked 16 Nov 2026
- Package
- kubernetes-mcp-server (npm)
Source · checked 16 Nov 2026
- Latest version
- 0.1.0
Source · checked 16 Nov 2026
- Last commit
- 14 Nov 2026
Source · checked 16 Nov 2026
- GitHub stars
- 2,250
Source · checked 16 Nov 2026
- Open issues
- 140
Source · checked 16 Nov 2026
Each value links to where it was found and shows the date it was checked. How we verify
Frequently asked questions
What does kubernetes-mcp-server do?
A Model Context Protocol (MCP) server for Kubernetes and OpenShift
Which MCP clients does kubernetes-mcp-server document setup for?
Its README documents setup for Claude Code, Claude Desktop, Cursor, VS Code, GitHub Copilot.
How do I install kubernetes-mcp-server?
Add the install config shown on this page to your MCP client's configuration; the package is kubernetes-mcp-server (npm). Check the README for client-specific steps.
What licence is kubernetes-mcp-server under?
Apache-2.0, as reported by the repository on 16 Nov 2026.
Is kubernetes-mcp-server still maintained?
The last commit was on 14 Nov 2026, and the repository had 140 open issues.
What tools does kubernetes-mcp-server expose?
78 tools: configuration_contexts_list, targets_list, configuration_view, events_list, namespaces_list, projects_list, nodes_log, nodes_stats_summary, nodes_top, pods_list, pods_list_in_namespace, pods_get, and more.
