MCP Kubernetes

v1.0.0โ€ขCloud Servicesโ€ขstable

๐ŸŽ๏ธ โ˜๏ธ/๐Ÿ  - MCP-K8S is an AI-driven Kubernetes resource management tool that allows users to operate any resources in Kubernetes clusters through natural language interaction, including native resources (like Deployment, Service) and custom resources (

debugkubernetesmcpmcp-server
Share:
146
Stars
0
Downloads
0
Weekly
0/5

What is MCP Kubernetes?

MCP Kubernetes is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐ŸŽ๏ธ โ˜๏ธ/๐Ÿ  - mcp-k8s is an ai-driven kubernetes resource management tool that allows users to operate any resources in kubernetes clusters through natural language interaction, including native resourc...

๐ŸŽ๏ธ โ˜๏ธ/๐Ÿ  - MCP-K8S is an AI-driven Kubernetes resource management tool that allows users to operate any resources in Kubernetes clusters through natural language interaction, including native resources (like Deployment, Service) and custom resources (

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • get-k8s-pod-logs
  • get-k8s-resource
  • k8s-pod-exec
  • list-k8s-contexts
  • list-k8s-events

Use Cases

Manage Kubernetes resources via natural language
Deploy and operate native and custom resources
Interact with clusters through AI agents
silenceper

Maintainer

LicenseApache-2.0
Languagego
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @strowk/mcp-k8s

Manual Installation

npx -y @strowk/mcp-k8s

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Kubernetes

MCP-K8S is an AI-driven Kubernetes resource management tool written in Go that bridges natural language interactions with Kubernetes clusters. It supports CRUD operations on native Kubernetes resources (Deployments, Services, ConfigMaps, and more), custom resources (CRDs), Helm chart management, and cluster diagnostics โ€” all without requiring users to know kubectl syntax. Teams can use it to deploy applications, inspect cluster state, debug issues, and manage Helm releases through conversational AI interfaces.

Prerequisites

  • A running Kubernetes cluster with a valid kubeconfig file (typically at ~/.kube/config)
  • Go 1.21+ if building from source, or a pre-built binary from the releases page
  • Helm installed if using Helm management features
  • An MCP-compatible client such as Claude Desktop or Cursor
1

Install the mcp-k8s binary

Install using Go's package manager. Alternatively, download a pre-built binary from the GitHub releases page for your platform.

go install github.com/silenceper/mcp-k8s/cmd/mcp-k8s@latest
2

Build from source (alternative)

Clone the repository and build the binary locally if you prefer not to use Go install.

git clone https://github.com/silenceper/mcp-k8s.git
cd mcp-k8s
make build
3

Configure your MCP client

Add mcp-k8s to your Claude Desktop or other MCP client configuration. Point to your kubeconfig file and enable only the operation types you need for safety.

{
  "mcpServers": {
    "mcp-k8s": {
      "command": "/path/to/mcp-k8s",
      "args": [
        "--kubeconfig", "/home/user/.kube/config",
        "--enable-create",
        "--enable-update",
        "--transport", "stdio"
      ]
    }
  }
}
4

Enable Helm support (optional)

If you want to manage Helm releases, add the relevant flags. By default, Helm operations are disabled for safety.

# Add these args to your MCP client config args array:
"--enable-helm-install"
"--enable-helm-upgrade"
"--enable-helm-uninstall"
5

Verify cluster connectivity

Test the setup by asking your AI assistant to list resources in your cluster. The server exposes get_resource, list_resources, and get_api_resources tools.

MCP Kubernetes Examples

Client configuration

Claude Desktop configuration for mcp-k8s with read and write access enabled.

{
  "mcpServers": {
    "mcp-k8s": {
      "command": "/usr/local/bin/mcp-k8s",
      "args": [
        "--kubeconfig", "/home/user/.kube/config",
        "--enable-list",
        "--enable-create",
        "--enable-update",
        "--enable-delete",
        "--transport", "stdio"
      ]
    }
  }
}

Prompts to try

Natural language commands you can issue to manage your Kubernetes cluster.

- "List all pods in the production namespace"
- "Show me the status of my nginx deployment"
- "Scale the api-server deployment to 3 replicas"
- "What events have occurred in the kube-system namespace in the last hour?"
- "Install the cert-manager Helm chart from the jetstack repo"

Troubleshooting MCP Kubernetes

Cannot connect to cluster or 'kubeconfig not found' error

Ensure the --kubeconfig path points to a valid kubeconfig file. Test with kubectl --kubeconfig /your/path get nodes to verify connectivity before starting the MCP server.

Write operations (create/update/delete) are refused

By default, write operations are disabled. Add --enable-create, --enable-update, and --enable-delete flags to your server args in the MCP client config, and ensure your kubeconfig user has the necessary RBAC permissions.

Helm commands fail with 'helm not found'

Install Helm on the same machine running mcp-k8s (https://helm.sh/docs/intro/install/) and ensure the helm binary is on your PATH. The server delegates Helm operations to the local helm CLI.

Frequently Asked Questions about MCP Kubernetes

What is MCP Kubernetes?

MCP Kubernetes is a Model Context Protocol (MCP) server that ๐ŸŽ๏ธ โ˜๏ธ/๐Ÿ  - mcp-k8s is an ai-driven kubernetes resource management tool that allows users to operate any resources in kubernetes clusters through natural language interaction, including native resources (like deployment, service) and custom resources ( It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Kubernetes?

Install via npm with the command: npx -y @strowk/mcp-k8s. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with MCP Kubernetes?

MCP Kubernetes works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Kubernetes free to use?

Yes, MCP Kubernetes is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-k8s": { "command": "npx", "args": ["-y", "@strowk/mcp-k8s"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use MCP Kubernetes?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides