kubernetes-mcp-server AGENTS.md

kubernetes-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from containers/kubernetes-mcp-server. It costs 2,111 tokens per session, scanned C, original, Apache-2.0.

Project instructions for coding agents working on a Go server that lets AI assistants manage Kubernetes and OpenShift clusters through MCP, a standard way for assistants to call tools. They describe the code layout, development workflow, and logging rules.

In plain words
What is it for?
Developing features, locating code, adding log messages, and working with the Kubernetes MCP server and its npm or Python distribution wrappers.
Why use it?
They give agents the project-specific context needed to change the server safely and keep new code consistent with its structure and logging practices.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/containers/kubernetes-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/containers/kubernetes-mcp-server

Made for: Codex, 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 kubernetes-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/containers/kubernetes-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/containers/kubernetes-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/containers/kubernetes-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/containers/kubernetes-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,111 This file is loaded in full into every session.
When invoked 2,111 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02111 $0.02111
Opus 5 $0.01056 $0.01056
Sonnet 5 $0.00422 $0.00422
Haiku 4.5 $0.00211 $0.00211

Measured 4d ago against content hash 03bca9297ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

kubernetes-mcp-server AGENTS.md scanned grade C with 1 finding 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 4d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

It reads the kubeconfig from the `--kubeconfig` flag, the `KUBECONFIG` environment variable, or defaults to `~/.kube/config`.
AGENTS.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Agents.md for Kubernetes MCP Server

This Agents.md file provides comprehensive guidance for AI assistants and coding agents (like Claude, Gemini, Cursor, and others) to work with this codebase.

This repository contains the kubernetes-mcp-server project, a powerful Go-based Model Context Protocol (MCP) server that provides native Kubernetes and OpenShift cluster management capabilities without external dependencies. This MCP server enables AI assistants (like Claude, Gemini, Cursor, and others) to interact with Kubernetes clusters using the Model Context Protocol (MCP).

Project Structure

Standard Go layout: cmd/kubernetes-mcp-server/ (entry point), pkg/ (libraries by domain). The npm/ and python/ directories only wrap the compiled binary for distribution — do not add features there. Build, test, and lint commands are in the Makefile.

Feature development

Logging

When adding log lines, always use a contextual logger (klogutil.FromContext(ctx) from pkg/klogutil). If necessary, add a ctx parameter to the function, and wire the context through to where you need a logger.

klogutil.FromContext wraps klog.FromContext and injects the context into the logger's values so the OpenTelemetry log bridge can extract the active trace span for log-trace correlation. Do not use klog.FromContext directly in production code.

If you start a new trace span (e.g. ctx, span := tracer.Start(ctx, "op")), you must call klogutil.FromContext(ctx) again to pick up the new span — the logger captured before the span was created still carries the old (or empty) span context.

Adding new MCP tools

The project uses a toolset-based architecture for organizing MCP tools:

  • Tool definitions are created in pkg/api/ using the ServerTool struct.
  • Toolsets group related tools together (e.g., config tools, core Kubernetes tools, Helm tools).
  • Registration happens in pkg/toolsets/ where toolsets are registered at initialization.
  • Each toolset lives in its own subdirectory under pkg/toolsets/ (e.g., pkg/toolsets/config/, pkg/toolsets/core/, pkg/toolsets/helm/).

Read the full file on GitHub · 210 lines

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. 4d ago First seen · 210 lines · 2,111 tokens per session scan C 03bca9297ad0

Subscribe to this mod's changes

kubernetes-mcp-server AGENTS.md is an instructions file published in the GitHub repository containers/kubernetes-mcp-server (2,052 stars, last pushed today), licensed Apache-2.0. It adds 2,111 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.