What is kube-mcp CLAUDE.md?

Development instructions for an MCP server that manages Kubernetes clusters through kubectl, a command-line tool for Kubernetes. They cover building, running, testing, and local inspection.

Use them to build or run the server, execute focused or complete tests, inspect it with the MCP Inspector, and test it locally with the provided chat client.

They give contributors the commands and testing guidance needed to develop the server without guessing how its TypeScript project or Kubernetes operations are organized.

How Abinesh0206/kube-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Abinesh0206/kube-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Abinesh0206/kube-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Abinesh0206/kube-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/abinesh0206/kube-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/abinesh0206/kube-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/abinesh0206/kube-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abinesh0206/kube-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/abinesh0206/kube-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abinesh0206/kube-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 828 This file is loaded in full into every session.

When invoked 828 The same file — it is already loaded in full.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00828	$0.00828
Opus 5.5	$0.00331	$0.00331
Sonnet 5.5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured 2mo ago against content hash 5ed32f344ceb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

kube-mcp CLAUDE.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 2mo 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.

- Server loads kubeconfig from multiple sources: KUBECONFIG_YAML env var, KUBECONFIG path, or ~/.kube/config

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mcp-server-kubernetes CLAUDE.md — 100% identical, 0 lines differ

CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

Build and Development

bun run build - Compile TypeScript to dist/ and make executables
bun run dev - Start TypeScript compiler in watch mode for development
bun run start - Run the compiled server from dist/index.js
bun run test - Run all tests using Vitest

Testing and Quality

bun run test - Execute the complete test suite with custom sequencer (kubectl tests run last)
Tests have 120s timeout and 60s hook timeout due to Kubernetes operations
Use npx @modelcontextprotocol/inspector node dist/index.js for local testing with Inspector
Always run single test based on with area you are working on. running all tests will take a long time.

Local Development Testing

bun run chat - Test locally with mcp-chat CLI client
For Claude Desktop testing, point to local dist/index.js build

Architecture Overview

This is an MCP (Model Context Protocol) server that provides Kubernetes cluster management capabilities. The server connects to Kubernetes clusters via kubectl and offers both read-only and destructive operations.

Core Components

KubernetesManager (src/utils/kubernetes-manager.ts): Central class managing Kubernetes API connections, resource tracking, port forwards, and watches. Handles kubeconfig loading from multiple sources in priority order.

Tool Structure: Each Kubernetes operation is implemented as a separate tool in src/tools/, with corresponding Zod schemas for validation. Tools are divided into:

kubectl operations (get, describe, apply, delete, create, etc.)
Helm operations (install, upgrade, uninstall charts)
Specialized operations (port forwarding, scaling, rollouts)

Resource Handlers (src/resources/handlers.ts): Manage MCP resource endpoints for dynamic data retrieval.

Configuration System (src/config/): Contains schemas and templates for deployments, namespaces, containers, and cleanup operations.

Read the full file on GitHub · 91 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.

2mo ago First seen · 91 lines · 828 tokens per session scan C 5ed32f344ceb

Subscribe to this mod's changes

kube-mcp CLAUDE.md is an instructions file published in the GitHub repository Abinesh0206/kube-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 828 tokens to every session, about $0.0033 per session on Opus 5.5. 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 2026-08-31.

Containers DevOps and cloud

kube-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kube-mcp CLAUDE.mdAbinesh0206/kube-mcp	Instructions file	0	1y ago	MIT	C	828	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

kube-mcp: Instructions file for Claude Code