Kubernetes MCP Server is a Model Context Protocol server that lets an AI client interact with Kubernetes and OpenShift clusters. It is used to inspect and manage cluster resources, pods, namespaces, events, Helm releases, and Tekton-related objects.
Borrowing it
Nothing to install: this file belongs to containers/kubernetes-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.
curl -O https://raw.githubusercontent.com/containers/kubernetes-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/containers/kubernetes-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/containers/kubernetes-mcp-server/agents-md)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02193 | $0.02193 |
| Opus 5.5 | $0.00877 | $0.00877 |
| Sonnet 5.5 | $0.00439 | $0.00439 |
| Haiku 4.5 | $0.00219 | $0.00219 |
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 7d 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` TOML option, the `KUBECONFIG` environment variable, or defaults to `~/.kube/config`. How it starts
The opening of the file, as written. The whole thing — 216 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 theServerToolstruct. - 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/).
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.
- 7d ago Changed · +6 lines · +82 tokens per session dd93bf480458
- 1mo ago Changed 1884e926ec9d
- 2mo ago First seen · 210 lines · 2,111 tokens per session scan C 03bca9297ad0
kubernetes-mcp-server AGENTS.md is an instructions file published in the GitHub repository containers/kubernetes-mcp-server (2,196 stars, last pushed today), licensed Apache-2.0. It adds 2,193 tokens to every session, about $0.0088 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.