k8s-pilot MCP Server

Use This MCP server To

Manage multiple Kubernetes clusters from a single control plane Perform CRUD operations on Kubernetes resources across clusters Switch contexts seamlessly between different Kubernetes clusters Monitor and observe cluster states centrally Automate cluster management workflows via APIs Integrate Kubernetes control with AI-driven tools using MCP

README

k8s-pilot-ci

The Central Pilot for Your Kubernetes Fleets ✈️✈️

k8s_pilot is a lightweight, centralized control plane server for managing multiple Kubernetes clusters at once.
With powerful tools and intuitive APIs, you can observe and control all your clusters from one cockpit.

🚀 Overview

🔄 Supports multi-cluster context switching
🔧 Enables CRUD operations on most common Kubernetes resources
⚙️ Powered by MCP for Claude AI and beyond

🧰 Prerequisites

Python 3.13 or higher
uv package manager
Access to Kubernetes clusters (~/.kube/config or in-cluster config)

# Install uv (if not installed)

# For MacOS
brew install uv

# For Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

Installation

# Clone the repository
git clone https://github.com/bourbonkk/k8s-pilot.git
cd k8s-pilot

# Launch with uv + MCP
uv run --with mcp[cli] mcp run k8s_pilot.py

Usage with Claude Desktop

Use this config to run k8s_pilot MCP server from within Claude:

{
  "mcpServers": {
    "k8s_pilot": {
      "command": "uv",
      "args": [
        "--directory",
        "<path-to-cloned-repo>/k8s-pilot",
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "k8s_pilot.py"
      ]
    }
  }
}

Replace with the actual directory where you cloned the repo.

Scenario

Create a Deployment using the nginx:latest image in the pypy namespace, and also create a Service that connects to it. deploy와 서비스생성(영어

Key Features

Multi-Cluster Management

Seamlessly interact with multiple Kubernetes clusters
Perform context-aware operations
Easily switch between clusters via MCP prompts

Resource Control

View, create, update, delete:
- Deployments, Services, Pods
- ConfigMaps, Secrets, Ingresses
- StatefulSets, DaemonSets
- Roles, ClusterRoles
- PersistentVolumes & Claims

Namespace Operations

Create/delete namespaces
List all resources in a namespace
Manage labels and resource quotas

Node Management

View node details and conditions
Cordon/uncordon, label/taint nodes
List pods per node

License

This project is licensed under the MIT License. See the LICENSE file for details.

k8s-pilot FAQ

What Kubernetes versions does k8s-pilot support?

k8s-pilot supports any Kubernetes cluster accessible via standard kubeconfig files, compatible with most Kubernetes versions.

How does k8s-pilot handle authentication to multiple clusters?

It uses your existing kubeconfig contexts and credentials to authenticate and switch between clusters securely.

What are the prerequisites for running k8s-pilot?

Requires Python 3.13+, the 'uv' package manager, and access to Kubernetes clusters via kubeconfig.

Can k8s-pilot perform all Kubernetes resource operations?

It supports CRUD operations on most common Kubernetes resources, enabling comprehensive cluster management.

How does k8s-pilot integrate with AI models?

Built on MCP, it enables AI models like Claude and Gemini to interact with Kubernetes clusters through structured APIs.

Is k8s-pilot suitable for large-scale Kubernetes fleets?

Yes, it is designed to manage multiple clusters efficiently from a centralized control plane.

How do I install k8s-pilot?

Install Python 3.13+, then use the 'uv' package manager to install k8s-pilot and configure your kubeconfig for cluster access.

Does k8s-pilot support real-time cluster monitoring?

Yes, it provides tools to observe cluster states and resource changes in real time.