agentmods.dev

k8s-mcp-server: Instructions file for Claude Code

CLAUDE.md

k8s-mcp-server CLAUDE.md is an instructions file for Claude Code from alexei-led/k8s-mcp-server. It costs 1,008 tokens per session, scanned A, original, MIT.

Development instructions for a Kubernetes MCP server, a service that lets an AI agent use Kubernetes tools. They describe the project structure, commands, tools, and security checks.

In plain words
What is it for?
Use them when developing the server, running unit or integration tests, checking code style, starting it locally, or reviewing kubectl command validation and security.
Why use it?
They give the agent the project-specific information needed to build, test, inspect, and safely change the server. They also explain how commands behave when kubectl or a cluster is unavailable.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is alexei-led/k8s-mcp-server's own configuration. It tells Claude Code how to work on k8s-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything k8s-mcp-server configures →

not rated 211repo +1 8mo ago A scan 1,008 tokens original MIT archived
View source ↗ alexei-led/k8s-mcp-server
Reuse

Borrowing it

Nothing to install: this file belongs to alexei-led/k8s-mcp-server. 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/alexei-led/k8s-mcp-server/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/alexei-led/k8s-mcp-server

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.

agentmods badge for k8s-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexei-led/k8s-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/alexei-led/k8s-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alexei-led/k8s-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/alexei-led/k8s-mcp-server/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.

agentmods 80×15 button for k8s-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alexei-led/k8s-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/alexei-led/k8s-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,008 This file is loaded in full into every session.
When invoked 1,008 The same file — it is already loaded in full.
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.
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 5.1 $0.01008 $0.01008
Opus 5.5 $0.00403 $0.00403
Sonnet 5.5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 2mo ago against content hash 09174d3eb88d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

k8s-mcp-server CLAUDE.md 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 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.

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.

CLAUDE.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

K8s MCP Server — Development Guide

Build & Test Commands

make install           # Install dependencies
make dev-install       # Install with dev deps
make test              # Unit tests only (default)
make test-all          # All tests (incl. integration)
make test-integration  # Integration tests (needs kubectl + cluster)
make lint              # ruff check src/ tests/
make format            # ruff format src/ tests/

Direct commands:

uv run pytest -q tests/unit/   # Fast unit tests
uvx ruff check src/ tests/     # Lint
python -m k8s_mcp_server        # Run server locally

Architecture

Server (src/k8s_mcp_server/server.py)

  • 8 tools: 4 execute_* + 4 describe_*, all delegating to _execute_tool_command() / _describe_tool_command()
  • CLI status checked at startup — tools gracefully error if CLI not installed
  • Uses FieldInfo workaround for Pydantic Field defaults in timeout parameter
  • ToolAnnotations: readOnlyHint=True for describe tools, destructiveHint=True, openWorldHint=True for execute tools

Security (src/k8s_mcp_server/security.py)

  • validate_command() — blocked patterns, required resource names for destructive ops
  • kubectl exec restrictions (no interactive shells)
  • Per-tool security rules validated before execution

Errors (src/k8s_mcp_server/errors.py)

  • Hierarchy: K8sMCPError → CommandValidationError, CommandExecutionError, AuthenticationError, CommandTimeoutError
  • create_error_result() produces structured CommandResult with ErrorDetails
  • Errors returned as tool results with isError=true (MCP spec compliant), not as JSON-RPC errors

CLI Executor (src/k8s_mcp_server/cli_executor.py)

  • execute_command() — asyncio subprocess, pipe support (| splitting), timeout
  • get_command_help() — fetches --help output
  • check_cli_installed() — startup validation

Tools (src/k8s_mcp_server/tools.py)

  • CommandResult: status, output, error (optional ErrorDetails), exit_code
  • CommandHelpResult: help_text, status, error

Read the full file on GitHub · 106 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. 2mo ago First seen · 106 lines · 1,008 tokens per session scan A 09174d3eb88d

Subscribe to this mod's changes

k8s-mcp-server CLAUDE.md is an instructions file published in the GitHub repository alexei-led/k8s-mcp-server (211 stars, last pushed 8mo ago), licensed MIT. It adds 1,008 tokens to every session, about $0.0040 per session on Opus 5.5. 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 2026-08-30.

ai-assistantargocdclaudedockerhelm
Related

k8s-mcp-server CLAUDE.md compared with instructions from other repositories

k8s-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
k8s-mcp-server CLAUDE.mdalexei-led/k8s-mcp-serverInstructions file2118mo agoMITA1,008Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode