Kubernetes

What is mcp-server-kubernetes?

mcp-server-kubernetes is a Model Context Protocol (MCP) server designed to connect with and manage Kubernetes clusters. It provides a unified API for various kubectl operations, allowing users to interact with their Kubernetes resources programmatically or through compatible MCP clients like Claude Desktop and mcp-chat.

How to use mcp-server-kubernetes?

To use mcp-server-kubernetes, you need to have kubectl installed and configured with a valid kubeconfig file. Helm v3 is optional if you plan to use Helm operations. The server can be run via npx mcp-server-kubernetes. For integration with Claude Desktop, you can configure it to use the server by adding a JSON entry to its mcpServers configuration. For command-line interaction, mcp-chat can be used to connect to the server.

Key Features of mcp-server-kubernetes

Kubernetes Cluster Connectivity: Connects to Kubernetes clusters and supports loading kubeconfig from multiple sources.
Unified kubectl API: Provides a comprehensive set of functions for managing Kubernetes resources, including get, describe, create, apply, delete, logs, context management, explain, list API resources, scale, patch, rollout, and a generic kubectl_generic command.
Advanced Operations: Supports scaling deployments, port forwarding to pods and services, and Helm operations (install, upgrade, uninstall charts).
Troubleshooting Prompt (k8s-diagnose): Offers a systematic troubleshooting flow for Kubernetes pods.
Non-Destructive Mode: Allows running the server in a read-only and create/update-only mode, disabling destructive operations for enhanced safety.

Use Cases of mcp-server-kubernetes

Automated Kubernetes Management: Integrate with automation scripts or tools to manage Kubernetes resources.
Interactive Cluster Management: Use with MCP clients like Claude Desktop or mcp-chat for interactive management and troubleshooting of Kubernetes clusters.
Development and Testing: Facilitate local development and testing workflows by providing a consistent interface for Kubernetes interactions.
Secure Operations: Utilize the non-destructive mode for environments where accidental deletion or modification of resources needs to be prevented.

FAQ from mcp-server-kubernetes

What are the prerequisites for using mcp-server-kubernetes? You need kubectl installed and in your PATH, a valid kubeconfig file with contexts configured, and access to a Kubernetes cluster. Helm v3 is required for Helm operations.
How can I verify my connection to the Kubernetes cluster? You can ask Claude to list your pods or create a test deployment. Alternatively, run kubectl get pods in a standard terminal to check your cluster connection.
How do I enable non-destructive mode? Set the environment variable ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS=true when running the server, or configure it in your Claude Desktop mcpServers environment variables.
What commands are disabled in non-destructive mode? Destructive operations like kubectl_delete, uninstall_helm_chart, cleanup, and potentially kubectl_generic are disabled.
Where can I find more advanced features and architectural details? Refer to the ADVANCED_README.md file in the project repository and the DeepWiki link provided in the README for architectural overview.

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

Usage with Claude Desktop

{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": ["mcp-server-kubernetes"]
    }
  }
}

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

The server will automatically connect to your current kubectl context. Make sure you have:

kubectl installed and in your PATH
A valid kubeconfig file with contexts configured
Access to a Kubernetes cluster configured for kubectl (e.g. minikube, Rancher Desktop, GKE, etc.)
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 asking Claude to list your pods or create a test deployment.

If you have errors open up a standard terminal and run kubectl get pods to see if you can connect to your cluster without credentials issues.

Usage with mcp-chat

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

npx mcp-chat --server "npx mcp-server-kubernetes"

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

Mac:

npx mcp-chat --config "~/Library/Application Support/Claude/claude_desktop_config.json"

Windows:

npx mcp-chat --config "%APPDATA%\Claude\claude_desktop_config.json"

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
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

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:

git clone https://github.com/Flux159/mcp-server-kubernetes.git
cd mcp-server-kubernetes
bun install

Development Workflow

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

bun run dev

Run unit tests:

bun run test

Build the project:

bun run build

Local Testing with Inspector

npx @modelcontextprotocol/inspector node dist/index.js
# Follow further instructions on terminal for Inspector link

Local testing with Claude Desktop

{
  "mcpServers": {
    "mcp-server-kubernetes": {
      "command": "node",
      "args": ["/path/to/your/mcp-server-kubernetes/dist/index.js"]
    }
  }
}

Local testing with mcp-chat

bun run 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.):

ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS=true npx mcp-server-kubernetes

For Claude Desktop configuration with non-destructive mode:

{
  "mcpServers": {
    "kubernetes-readonly": {
      "command": "npx",
      "args": ["mcp-server-kubernetes"],
      "env": {
        "ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS": "true"
      }
    }
  }
}

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
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
kubectl_generic: General kubectl command access (may include destructive operations)

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:

sequenceDiagram participant Client participant Transport as Transport Layer participant Server as MCP Server participant Filter as Tool Filter participant Handler as Request Handler participant K8sManager as KubernetesManager participant K8s as Kubernetes API Note over Transport: StdioTransport or<br>SSE Transport Client->>Transport: Send Request Transport->>Server: Forward Request alt Tools Request Server->>Filter: Filter available tools Note over Filter: Remove destructive tools<br>if in non-destructive mode Filter->>Handler: Route to tools handler alt kubectl operations Handler->>K8sManager: Execute kubectl operation K8sManager->>K8s: Make API call else Helm operations Handler->>K8sManager: Execute Helm operation K8sManager->>K8s: Make API call else Port Forward operations Handler->>K8sManager: Set up port forwarding K8sManager->>K8s: Make API call end K8s-->>K8sManager: Return result K8sManager-->>Handler: Process response Handler-->>Server: Return tool result else Resource Request Server->>Handler: Route to resource handler Handler->>K8sManager: Get resource data K8sManager->>K8s: Query API K8s-->>K8sManager: Return data K8sManager-->>Handler: Format response Handler-->>Server: Return resource data end Server-->>Transport: Send Response Transport-->>Client: Return Final Response

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.

Kubernetes Overview