Advertise
MCP.so
Sign In

MCP Kubernetes Server

@MCP-Mirror

Repository

Basic information

Category

Cloud & Infrastructure

Transports

stdio

Author

MCP-Mirror

About MCP Kubernetes Server

Mirror of

#mcp#kubernetes#llm-integration

MCP Kubernetes Server config

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

{
  "mcpServers": {
    "abhijeetka_mcp-k8s-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@abhijeetka/mcp-k8s-server",
        "--client",
        "claude"
      ]
    }
  }
}

MCP Kubernetes Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Kubernetes Server?

MCP Kubernetes Server is an MCP (Model Context Protocol) server that provides control over Kubernetes clusters through interactions with LLMs. It wraps kubectl commands to offer a simple interface for managing Kubernetes resources, enabling seamless interaction between language models and Kubernetes operations.

How to use MCP Kubernetes Server?

Install via Smithery or configure the MCP server in your Claude Desktop config (e.g., using uv to run kubernetes.py). The server exposes tools that LLMs can call using natural language prompts such as "Create a new nginx deployment with 3 replicas."

Key features of MCP Kubernetes Server

  • Wraps kubectl commands for common Kubernetes operations.
  • Supports create, scale, update, delete, and inspect resources.
  • Includes port-forward, expose, label, and annotation management.
  • Provides context switching and namespace-aware operations.
  • Designed for natural language interaction through LLMs.

Use cases of MCP Kubernetes Server

  • Manage deployments, pods, services, and other resources via conversational prompts.
  • Automate cluster operations without memorizing kubectl syntax.
  • Enable LLMs to maintain context across multi-step Kubernetes tasks.
  • Validate and execute resource changes with reduced command complexity.

Frequently asked questions

1

What do I need to run the server?

You need Python 3.x, the MCP framework, and Kubernetes cluster access configured via `kubectl`.

2

How does the server interact with LLMs?

Each tool function is decorated with `@mcp.tool()`, making them accessible to LLMs through the Model Context Protocol.

3

Can I use it with Claude Desktop?

Yes. Add a JSON entry to your Claude Desktop config with the appropriate command (e.g., `uv run kubernetes.py`).

4

What if I want to install it automatically?

Run `npx -y @smithery/cli install @abhijeetka/mcp-k8s-server --client claude` via Smithery.

5

Are there any security considerations?

Yes. Ensure proper access controls on your cluster, run the MCP server in a secure environment, and authenticate/authorize API access.

Comments

More Cloud & Infrastructure MCP servers

container-use

aluzzardi

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

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

Webshare

Webshare

The official Webshare MCP server. Manage your proxies, usage, plans and billing from Claude, Cursor or any MCP client. Sign in with OAuth, no API key.

SnapDeploy MCP

AAR-Labs

Deploy and manage SnapDeploy apps (Docker containers on AWS) from Claude Code, Cursor, Codex or Gemini CLI: builds, logs, env vars, add-ons, domains.

Aws Kb Retrieval Server

modelcontextprotocol

Model Context Protocol Servers

88.2K
Advertise