k8s-mcp-server

k8s-mcp-server is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from VersusControl/devops-ai-guidelines. Its token cost is not measured, scanned A, original, MIT.

A configured tool server that connects an agent to a Kubernetes cluster through the Model Context Protocol (MCP), a standard way for an AI tool to expose external actions and data.

In plain words
What is it for?
Use it as the infrastructure connection for inspecting or operating Kubernetes resources and workloads.
Why use it?
It provides the connection details needed for Kubernetes operations without describing or granting permissions itself. The server can then be used by an agent mode that supports its tools.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

Good fit Use it as the infrastructure connection for inspecting or operating Kubernetes resources and workloads.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server

Installing this writes the configuration, not the program: `${workspaceFolder}/code/04/bin/k8s-mcp-server` has to be on your PATH already, or the server will not start.

About the project

DevOps AI Guidelines is a learning and guidance repository for using artificial intelligence in DevOps, including paths toward AI infrastructure architecture and enterprise adoption. It is for DevOps engineers, teams introducing AI, and technical leaders planning AI-enabled operations. The catalogue instruction provides an agent-facing part of these guidelines.

VersusControl/devops-ai-guidelines · 1,526 stars · on GitHub · versusincident.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/VersusControl/devops-ai-guidelines

Installing this writes the configuration, not the program: `${workspaceFolder}/code/04/bin/k8s-mcp-server` has to be on your PATH already, or the server will not start.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for k8s-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server/github.svg)](https://agentmods.dev/mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server)
Your own site
<a href="https://agentmods.dev/mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server"><img src="https://agentmods.dev/badge/mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for k8s-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server"><img src="https://agentmods.dev/badge/mcp/versuscontrol/devops-ai-guidelines/vscode-k8s-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

k8s-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

02-mcp-for-devops/.vscode/mcp.json · 7 lines

What it actually says

{
  "k8s-mcp-server": {
    "type": "stdio",
    "command": "${workspaceFolder}/code/04/bin/k8s-mcp-server",
    "args": []
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 7 lines scan A 441c4741476e

Subscribe to this mod's changes

k8s-mcp-server is an MCP server published in the GitHub repository VersusControl/devops-ai-guidelines (1,526 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.