mcp-server-kubernetes

MCP Server Kubernetes

MCP Server that can connect to a Kubernetes cluster and manage it. Supports loading kubeconfig from multiple sources in priority order.

https://github.com/user-attachments/assets/f25f8f4e-4d04-479b-9ae0-5dac452dd2ed

Installation & Usage

Prerequisites

Before using this MCP server with any tool, make sure you have:

1. kubectl installed and in your PATH
2. A valid kubeconfig file with contexts configured
3. Access to a Kubernetes cluster configured for kubectl (e.g. minikube, Rancher Desktop, GKE, etc.)
4. Helm v3 installed and in your PATH (no Tiller required). Optional if you don't plan to use Helm.

You can verify your connection by running kubectl get pods in a terminal to ensure you can connect to your cluster without credential issues.

By default, the server loads kubeconfig from ~/.kube/config. For additional authentication options (environment variables, custom paths, etc.), see ADVANCED_README.md.

Claude Code

Add the MCP server to Claude Code using the built-in command:

This will automatically configure the server in your Claude Code MCP settings.

Claude Desktop

Add the following configuration to your Claude Desktop config file:

VS Code

For VS Code integration, you can use the MCP server with extensions that support the Model Context Protocol:

1. Install a compatible MCP extension (such as Claude Dev or similar MCP clients)
2. Configure the extension to use this server:

Cursor

Cursor supports MCP servers through its AI integration. Add the server to your Cursor MCP configuration:

The server will automatically connect to your current kubectl context. You can verify the connection by asking the AI assistant to list your pods or create a test deployment.

Usage with mcp-chat

mcp-chat is a CLI chat client for MCP servers. You can use it to interact with the Kubernetes server.

Alternatively, pass it your existing Claude Desktop configuration file from above (Linux should pass the correct path to config):

Mac:

Windows:

Features

• Connect to a Kubernetes cluster
• Unified kubectl API for managing resources
  • Get or list resources with kubectl_get
  • Describe resources with kubectl_describe
  • List resources with kubectl_get
  • Create resources with kubectl_create
  • Apply YAML manifests with kubectl_apply
  • Delete resources with kubectl_delete
  • Get logs with kubectl_logs
  • Manage kubectl contexts with kubectl_context
  • Explain Kubernetes resources with explain_resource
  • List API resources with list_api_resources
  • Scale resources with kubectl_scale
  • Update field(s) of a resource with kubectl_patch
  • Manage deployment rollouts with kubectl_rollout
  • Execute any kubectl command with kubectl_generic
  • Verify connection with ping
• Advanced operations
  • Scale deployments with kubectl_scale (replaces legacy scale_deployment)
  • Port forward to pods and services with port_forward
  • Run Helm operations
    • Install, upgrade, and uninstall charts
    • Support for custom values, repositories, and versions
    • Template-based installation (helm_template_apply) to bypass authentication issues
    • Template-based uninstallation (helm_template_uninstall) to bypass authentication issues
  • Pod cleanup operations
    • Clean up problematic pods (cleanup_pods) in states: Evicted, ContainerStatusUnknown, Completed, Error, ImagePullBackOff, CrashLoopBackOff
  • Node management operations
    • Cordoning, draining, and uncordoning nodes (node_management) for maintenance and scaling operations
• Troubleshooting Prompt (k8s-diagnose)
  • Guides through a systematic Kubernetes troubleshooting flow for pods based on a keyword and optional namespace.
• Non-destructive mode for read and create/update-only access to clusters
• Secrets masking for security (masks sensitive data in kubectl get secrets commands, does not affect logs)

Prompts

The MCP Kubernetes server includes specialized prompts to assist with common diagnostic operations.

/k8s-diagnose Prompt

This prompt provides a systematic troubleshooting flow for Kubernetes pods. It accepts a keyword to identify relevant pods and an optional namespace to narrow the search. The prompt's output will guide you through an autonomous troubleshooting flow, providing instructions for identifying issues, collecting evidence, and suggesting remediation steps.

Local Development

Make sure that you have bun installed. Clone the repo & install dependencies:

Development Workflow

1. Start the server in development mode (watches for file changes):

2. Run unit tests:

3. Build the project:

4. Local Testing with Inspector

5. Local testing with Claude Desktop

6. Local testing with mcp-chat

Contributing

See the CONTRIBUTING.md file for details.

Advanced

Non-Destructive Mode

You can run the server in a non-destructive mode that disables all destructive operations (delete pods, delete deployments, delete namespaces, etc.):

For Claude Desktop configuration with non-destructive mode:

Commands Available in Non-Destructive Mode

All read-only and resource creation/update operations remain available:

• Resource Information: kubectl_get, kubectl_describe, kubectl_logs, explain_resource, list_api_resources
• Resource Creation/Modification: kubectl_apply, kubectl_create, kubectl_scale, kubectl_patch, kubectl_rollout
• Helm Operations: install_helm_chart, upgrade_helm_chart, helm_template_apply, helm_template_uninstall
• Connectivity: port_forward, stop_port_forward
• Context Management: kubectl_context

Commands Disabled in Non-Destructive Mode

The following destructive operations are disabled:

• kubectl_delete: Deleting any Kubernetes resources
• uninstall_helm_chart: Uninstalling Helm charts
• cleanup: Cleanup of managed resources
• cleanup_pods: Cleaning up problematic pods
• node_management: Node management operations (can drain nodes)
• kubectl_generic: General kubectl command access (may include destructive operations)

Helm Template Apply Tool

The helm_template_apply tool provides an alternative way to install Helm charts that bypasses authentication issues commonly encountered with certain Kubernetes configurations. This tool is particularly useful when you encounter errors like:

Instead of using helm install directly, this tool:

1. Uses helm template to generate YAML manifests from the Helm chart
2. Applies the generated YAML using kubectl apply
3. Handles namespace creation and cleanup automatically

Usage Example

This is equivalent to running:

Parameters

• name: Release name for the Helm chart
• chart: Chart name or path to chart directory
• repo: Chart repository URL (optional if using local chart path)
• namespace: Kubernetes namespace to deploy to
• values: Chart values as an object (optional)
• valuesFile: Path to values.yaml file (optional, alternative to values object)
• createNamespace: Whether to create the namespace if it doesn't exist (default: true)

Pod Cleanup with Existing Tools

Pod cleanup can be achieved using the existing kubectl_get and kubectl_delete tools with field selectors. This approach leverages standard Kubernetes functionality without requiring dedicated cleanup tools.

Identifying Problematic Pods

Use kubectl_get with field selectors to identify pods in problematic states:

Get failed pods:

Get completed pods:

Get pods with specific conditions:

Deleting Problematic Pods

Use kubectl_delete with field selectors to delete pods in problematic states:

Delete failed pods:

Delete completed pods:

Workflow

1. First, identify problematic pods using kubectl_get with appropriate field selectors
2. Review the list of pods in the response
3. Delete the pods using kubectl_delete with the same field selectors

Available Field Selectors

• status.phase=Failed - Pods that have failed
• status.phase=Succeeded - Pods that have completed successfully
• status.phase=Pending - Pods that are pending
• status.conditions[?(@.type=='Ready')].status=False - Pods that are not ready

Safety Features

• Field selectors: Target specific pod states precisely
• Force deletion: Use force=true and gracePeriodSeconds=0 for immediate deletion
• Namespace isolation: Target specific namespaces or use allNamespaces=true
• Standard kubectl: Uses well-established Kubernetes patterns

Node Management Tool

The node_management tool provides comprehensive node management capabilities for Kubernetes clusters, including cordoning, draining, and uncordoning operations. This is essential for cluster maintenance, scaling, and troubleshooting.

Operations Available

• list: List all nodes with their status and schedulability
• cordon: Mark a node as unschedulable (no new pods will be scheduled)
• drain: Safely evict all pods from a node and mark it as unschedulable
• uncordon: Mark a node as schedulable again

Usage Examples

1. List all nodes:

2. Cordon a node (mark as unschedulable):

3. Drain a node (dry run first):

4. Drain a node (with confirmation):

5. Uncordon a node:

Drain Operation Parameters

• force: Force the operation even if there are pods not managed by controllers
• gracePeriod: Period of time in seconds given to each pod to terminate gracefully
• deleteLocalData: Delete local data even if emptyDir volumes are used
• ignoreDaemonsets: Ignore DaemonSet-managed pods (default: true)
• timeout: The length of time to wait before giving up (e.g., '5m', '1h')
• dryRun: Show what would be done without actually doing it
• confirmDrain: Explicit confirmation to drain the node (required for actual draining)

Safety Features

• Dry run by default: Drain operations default to dry run to show what would be done
• Explicit confirmation: Drain operations require confirmDrain=true to proceed
• Status tracking: Shows node status before and after operations
• Timeout protection: Configurable timeouts to prevent hanging operations
• Graceful termination: Configurable grace periods for pod termination

Common Use Cases

1. Cluster Maintenance: Cordon nodes before maintenance, drain them, perform maintenance, then uncordon
2. Node Scaling: Drain nodes before removing them from the cluster
3. Troubleshooting: Isolate problematic nodes by cordoning them
4. Resource Management: Drain nodes to redistribute workload

For additional advanced features, see the ADVANCED_README.md.

Architecture

See this DeepWiki link for a more indepth architecture overview created by Devin.

This section describes the high-level architecture of the MCP Kubernetes server.

Request Flow

The sequence diagram below illustrates how requests flow through the system:

See this DeepWiki link for a more indepth architecture overview created by Devin.

Publishing new release

Go to the releases page, click on "Draft New Release", click "Choose a tag" and create a new tag by typing out a new version number using "v{major}.{minor}.{patch}" semver format. Then, write a release title "Release v{major}.{minor}.{patch}" and description / changelog if necessary and click "Publish Release".

This will create a new tag which will trigger a new release build via the cd.yml workflow. Once successful, the new release will be published to npm. Note that there is no need to update the package.json version manually, as the workflow will automatically update the version number in the package.json file & push a commit to main.

Not planned

Adding clusters to kubectx.

Star History

🖊️ Cite

If you find this repo useful, please cite: