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/skills/toolset-design/SKILL.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/skills/containers/kubernetes-mcp-server/toolset-design)<a href="https://agentmods.dev/skills/containers/kubernetes-mcp-server/toolset-design"><img src="https://agentmods.dev/badge/skills/containers/kubernetes-mcp-server/toolset-design/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/skills/containers/kubernetes-mcp-server/toolset-design"><img src="https://agentmods.dev/badge/skills/containers/kubernetes-mcp-server/toolset-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 180 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00069 | $0.04205 |
| Opus 5.5 | $0.00028 | $0.01682 |
| Sonnet 5.5 | $0.00014 | $0.00841 |
| Haiku 4.5 | $0.00007 | $0.00421 |
Grade B, and why
toolset-design scanned grade B 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 11d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
The core toolset provides `pods_exec` which can run arbitrary commands in pods. How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toolset Design Guide
This skill codifies the methodology for designing MCP tools and toolsets in this repository. The core principle is eval-first, tools-second: prove the need before writing the code.
Phase 1: Validate the need with evals
Before writing any toolset code, write eval tasks that represent what a user would actually ask an LLM to do in the target domain. This serves two purposes:
-
Baseline: Run the evals with only the existing toolsets enabled (core, config, etc.). If the LLM can already accomplish the tasks using
pods_exec,resources_list, or other generic tools, you may not need dedicated tools at all. -
Gap identification: The tasks where the baseline fails (or produces poor results) reveal the actual gaps that new tools should fill.
How to write eval tasks
Create tasks under evals/tasks/<domain>/ using the mcpchecker/v1alpha2 format.
See existing tasks in evals/tasks/ for examples at different difficulty levels.
Design tasks that represent real user workflows, not tool-shaped requests:
# BAD: This is testing a tool, not a workflow
prompt:
inline: Run helm list --all-namespaces
# GOOD: This is testing what a user would actually ask
prompt:
inline: What Helm releases are deployed across the cluster?
# BETTER: This tests whether the LLM can solve a real problem
prompt:
inline: >
The application in namespace "payments" was working yesterday but
is failing after a recent Helm upgrade. Investigate what changed
in the latest release and identify the issue.
Task difficulty should span the range:
- Easy: Simple queries (list resources, show config)
- Medium: Filtered/analyzed output (find specific entries matching a pattern, correlate data across sources)
- Hard: Multi-step diagnosis (investigate root cause, identify misconfiguration, suggest fix)
Running the baseline
# Run evals with only core+config toolsets to establish baseline
mcpchecker check evals/core-eval-testing/<agent>/eval-core.yaml --label-selector suite=<your-domain>
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.
- 11d ago Changed · +69 lines 21f782ed968a
- 2mo ago First seen · 292 lines · 69 tokens per session scan B adaa834ce8e4
toolset-design is a skill published in the GitHub repository containers/kubernetes-mcp-server (2,196 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 4,205 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mirrord-kafka
Helps DevOps engineers configure mirrord Operator's Kafka queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs (the current resources; MirrordKafkaTopicsConsumer + MirrordKafkaClientConfig are deprecated but still supported), the matching mirrord.json…
mirrord-propagation-discovery
Scans a live Kubernetes environment with mirrord dump to find an identifier mirrord can filter traffic on: a header, a baggage or tracestate member, a tenant or user id, a trace id (W3C, B3, X-Ray, Google, Jaeger), a JWT claim, a cookie, a path segment, or a JSON body field that is present on every hop of a request…
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.
detecting-container-drift-at-runtime
Detect unauthorized modifications to running containers by monitoring for binary execution drift, file system changes, and configuration deviations from the original container image.
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-kubernetes-network-policy-with-calico
Implement Kubernetes network segmentation using Calico NetworkPolicy and GlobalNetworkPolicy for zero-trust pod-to-pod communication.