Kubernetes MCP Server

@wakeupworld

About Kubernetes MCP Server

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "k8s_mcp_server": {
      "command": "python3",
      "args": [
        "k8s_mcp_wrapper.py"
      ]
    }
  }
}

Tools

Get a list of pods in the specified namespace

Get a list of services in the specified namespace

Get a list of deployments in the specified namespace

Get a list of all namespaces in the cluster

Describe a Kubernetes resource in detail

Get logs from a pod in the specified namespace

Create a new namespace in the Kubernetes cluster

Delete a Kubernetes resource

Scale a deployment to the specified number of replicas

Get events from the Kubernetes cluster

Get the current kubectl context

Get the list of available kubectl contexts

Switch the kubectl context

List all available scripts with their parameters

Overview

What is Kubernetes MCP Server?

A flexible Machine Communication Protocol (MCP) server that provides Kubernetes management capabilities with support for custom extension scripts. It integrates with kubectl to offer a wide range of cluster operations through tabular output, and automatically detects and registers user-created Python scripts as additional tools.

How to use Kubernetes MCP Server?

Install dependencies (Python 3.10+ and kubectl required), then run python3 k8s_mcp_wrapper.py from the bin/ directory. For development and debugging, use the --dev flag with an optional --dev-port. The scripts directory can be overridden by setting the SCRIPTS_DIR environment variable.

Key features of Kubernetes MCP Server

Implements MCP protocol using the official MCP SDK.
Provides built-in tools for common Kubernetes operations.
Supports dynamic loading and auto-detection of custom extension scripts.
Automatic parameter detection and validation for scripts.
Clean, modular architecture with Pydantic models for type safety.

Use cases of Kubernetes MCP Server

Manage Kubernetes resources (pods, services, deployments, namespaces) through MCP-based clients.
Retrieve logs, describe resources, and scale deployments programmatically.
Switch between kubectl contexts and list available contexts.
Extend functionality by adding custom Python scripts that are automatically registered as tools.

FAQ from Kubernetes MCP Server

What Python version is required?

Python 3.10 or higher is required by the MCP SDK.

What are the prerequisites?

kubectl must be installed and configured, and the Python packages listed in requirements.txt must be installed.

How do I create custom extension scripts?

Scripts must be Python files with a .py extension, use argparse for parameter definitions, and support receiving arguments via a JSON file with the --args-file flag. A detailed template is provided in the README.

Can I override the default scripts directory?

Yes, set the SCRIPTS_DIR environment variable to the desired path before starting the server.

What built-in tools are available?

Tools include get_pods, get_services, get_deployments, get_namespaces, describe_resource, get_pod_logs, create_namespace, delete_resource, scale_deployment, get_events, get_current_context, get_available_contexts, switch_context, and list_scripts.

Frequently asked questions

What Python version is required?

Python 3.10 or higher is required by the MCP SDK.

What are the prerequisites?

kubectl must be installed and configured, and the Python packages listed in `requirements.txt` must be installed.

How do I create custom extension scripts?

Scripts must be Python files with a `.py` extension, use `argparse` for parameter definitions, and support receiving arguments via a JSON file with the `--args-file` flag. A detailed template is provided in the README.

Can I override the default scripts directory?

Yes, set the `SCRIPTS_DIR` environment variable to the desired path before starting the server.

What built-in tools are available?

Tools include `get_pods`, `get_services`, `get_deployments`, `get_namespaces`, `describe_resource`, `get_pod_logs`, `create_namespace`, `delete_resource`, `scale_deployment`, `get_events`, `get_current_context`, `get_available_contexts`, `switch_context`, and `list_scripts`.

Comments

Basic information

More Cloud & Infrastructure MCP servers

Cloudflare MCP Server

cloudflare

3.9K

Kilo IoT Platform

Kilo IoT

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a

MCP Server that interacts with Azure AI Foundry (experimental)

azure-ai-foundry

A MCP Server for Azure AI Foundry: it's now moved to cloud, check the new Foundry MCP Server

252

container-use

aluzzardi

Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

3.9K

AWS Model Context Protocol (MCP) Server

alexei-led

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.

184