Back to MCP Catalog

Kubernetes Management MCP Server

Cloud PlatformsTypeScript
Manage Kubernetes clusters directly from your AI assistant
Available Tools

list_pods

List all pods in a namespace with their status, ready state, restarts, and age

namespace

describe_pod

Get detailed information about a specific pod

namenamespace

create_pod

Create a new pod with specified configuration

nameimagenamespacelabelsenvportsvolumescommandsargs

delete_pod

Delete a pod from the cluster

namenamespace

list_deployments

List all deployments in a namespace with their ready state, up-to-date, available, and age

namespace

create_deployment

Create a new deployment with specified configuration

nameimagereplicasnamespacelabelsenvportsvolumescommandsargs

scale_deployment

Scale a deployment to a specified number of replicas

namereplicasnamespace

delete_deployment

Delete a deployment from the cluster

namenamespace

list_services

List all services in a namespace with their type, cluster-IP, external-IP, ports, and age

namespace

create_service

Create a new service with specified configuration

nametypeportsselectornamespace

delete_service

Delete a service from the cluster

namenamespace

list_namespaces

List all namespaces in the cluster with their status and age

create_namespace

Create a new namespace in the cluster

namelabels

delete_namespace

Delete a namespace and all its resources from the cluster

name

list_nodes

List all nodes in the cluster with their status, roles, version, and age

describe_node

Get detailed information about a specific node

name

get_logs

Get logs from a pod for debugging

namenamespacecontainerprevioussincetailtimestamps

list_configmaps

List all ConfigMaps in a namespace

namespace

create_configmap

Create a new ConfigMap with specified data

namenamespacedata

get_configmap

Get the contents of a ConfigMap

namenamespace

delete_configmap

Delete a ConfigMap from the cluster

namenamespace

list_helm_releases

List all Helm releases in a namespace

namespace

install_helm_chart

Install a Helm chart with specified values

namechartnamespaceversionvaluesrepo

uninstall_helm_release

Uninstall a Helm release

namenamespace

upgrade_helm_release

Upgrade an existing Helm release

namechartnamespaceversionvaluesrepo

Kubernetes Management provides a seamless interface between AI assistants and Kubernetes clusters. It enables users to perform a wide range of Kubernetes operations through natural language, including pod management, deployment configuration, service creation, and Helm chart installation. This tool bridges the gap between complex Kubernetes commands and intuitive conversation, making cluster management more accessible.

Overview

Kubernetes Management allows you to interact with and manage your Kubernetes clusters directly through your AI assistant. This powerful integration enables you to perform common Kubernetes operations using natural language instead of remembering complex kubectl commands and syntax.

Prerequisites

Before using this tool, ensure you have:

  1. kubectl installed and available in your PATH
  2. A valid kubeconfig file with properly configured contexts
  3. Access to a Kubernetes cluster (minikube, Rancher Desktop, GKE, EKS, AKS, etc.)
  4. Helm v3 installed and in your PATH (optional, only needed for Helm operations)

Installation

To use the Kubernetes Management MCP with Claude Desktop, add the following configuration to your Claude Desktop config file:

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

The config file is typically located at:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

Alternative Usage with mcp-chat

You can also use this tool with mcp-chat, a CLI chat client for MCP servers:

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

Or by referencing your existing Claude Desktop configuration:

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

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

Verifying Connection

After installation, you can verify your connection by asking your AI assistant to list your pods or namespaces. If you encounter any errors, try running kubectl get pods in a terminal to check if you can connect to your cluster without credential issues.

Usage Examples

Here are some examples of what you can ask your AI assistant to do with Kubernetes Management:

  • "List all pods in the default namespace"
  • "Create a new deployment with 3 replicas of nginx"
  • "Scale the frontend deployment to 5 replicas"
  • "Show me the logs for the database pod"
  • "Install the Prometheus Helm chart"
  • "Create a ConfigMap with these environment variables"
  • "Delete the test namespace and all its resources"

Troubleshooting

If you encounter issues:

  1. Authentication Problems: Ensure your kubeconfig is properly set up and you have the necessary permissions
  2. Context Issues: Verify you're using the correct kubectl context with kubectl config current-context
  3. Helm Errors: Make sure Helm v3 is installed and properly configured
  4. Path Problems: Confirm kubectl and helm are in your system PATH

For more advanced usage and configuration options, refer to the project's GitHub repository.

Related MCPs

AWS CLI
Cloud PlatformsPython

Execute AWS CLI commands securely through AI assistants

Kubernetes
Cloud PlatformsGo

Connect to and manage Kubernetes clusters through natural language

Cloudflare
Cloud PlatformsTypeScript

A Model Context Protocol server for Cloudflare services

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.