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.
npx skills add Tobewont/k8s-mcp-server --skill k8s-managegit clone --depth 1 https://github.com/Tobewont/k8s-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/tobewont/k8s-mcp-server/k8s-manage)<a href="https://agentmods.dev/skills/tobewont/k8s-mcp-server/k8s-manage"><img src="https://agentmods.dev/badge/skills/tobewont/k8s-mcp-server/k8s-manage/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/tobewont/k8s-mcp-server/k8s-manage"><img src="https://agentmods.dev/badge/skills/tobewont/k8s-mcp-server/k8s-manage.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 | $0.00000 | $0.04235 |
| Opus 5.5 | $0.00000 | $0.01694 |
| Sonnet 5.5 | $0.00000 | $0.00847 |
| Haiku 4.5 | $0.00000 | $0.00424 |
Grade A, and why
k8s-manage scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `import_cluster` | 导入集群配置(传入服务端文件路径或内容均可;含证书的 kubeconfig 建议先尝试直接传内容,若服务端校验失败则按错误信息中的 curl 指引上传文件后传路径,见下方「导入集群」流程) | `name`, `kubeconfig`(文件路径或内容), `is_default` | How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kubernetes Cluster Management
通过 K8s MCP Server 管理 Kubernetes 集群。支持多种 MCP 连接方式(mcporter、Cursor 内置 MCP、SSE / Streamable HTTP),覆盖集群信息查询、工作负载 CRUD、诊断、备份恢复、节点运维等 35 个工具。
环境变量
使用本 Skill 前,用户需要提供以下信息(按连接方式选填):
| 变量 | 说明 | 示例 |
|---|---|---|
K8S_MCP_URL |
MCP Server 的 Streamable HTTP / SSE 地址 | http://localhost:8000/mcp |
K8S_MCP_TOKEN |
JWT 认证 Token(MCP Server 启用认证时必填) | eyJhbGciOi... |
K8S_MCP_SERVER |
mcporter 中注册的 MCP Server 名称 | k8s-mcp-server |
MCP 连接方式
本 Skill 支持三种方式调用 K8s MCP Server,按优先级自动选择:
方式一:Cursor 内置 MCP(推荐)
如果 K8s MCP Server 已在 Cursor 的 MCP 配置中注册(~/.cursor/mcp.json 或项目 .cursor/mcp.json),直接使用 CallMcpTool 调用:
{
"mcpServers": {
"k8s-mcp-server": {
"url": "http://localhost:8000/mcp"
}
}
}
调用方式:
CallMcpTool(server="k8s-mcp-server", toolName="<工具名>", arguments={...})
带认证时,需要在 MCP 配置的 headers 中加上 Token:
{
"mcpServers": {
"k8s-mcp-server": {
"url": "http://localhost:8000/mcp",
"headers": {
"Authorization": "Bearer <K8S_MCP_TOKEN>"
}
}
}
}
方式二:mcporter 命令行
mcporter 配置(~/.mcporter/config.json 或项目下 .mcporter.json):
{
"mcpServers": {
"k8s-mcp-server": {
"url": "http://localhost:8000/mcp",
"transport": "http",
"headers": {
"Authorization": "Bearer <K8S_MCP_TOKEN>"
}
}
}
}
调用格式:
mcporter call k8s-mcp-server.<工具名> --args '<JSON参数>'
无认证时省略 headers。查看可用工具列表:
mcporter tools k8s-mcp-server
方式三:stdio 模式(本地直连)
无需 HTTP 服务,直接通过 stdio 启动 MCP Server:
Cursor MCP 配置:
{
"mcpServers": {
"k8s-mcp-server": {
"command": "k8s-mcp-server",
"args": ["--transport", "stdio"],
"cwd": "<k8s-mcp-server项目路径>"
}
}
}
mcporter 配置:
{
"mcpServers": {
"k8s-mcp-server": {
"command": "k8s-mcp-server",
"args": ["--transport", "stdio"],
"cwd": "<k8s-mcp-server项目路径>",
"transport": "stdio"
}
}
}
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 · 428 lines · 0 tokens per session scan A 67f6a42d6291
k8s-manage is a skill published in the GitHub repository Tobewont/k8s-mcp-server (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,235 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
k8s-manage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| k8s-manageTobewont/k8s-mcp-server | Skill | 2 | 3mo ago | MIT | A | 0 | Claude Code, Codex |
| openshell-cliNVIDIA/OpenShell | Skill | 21k | today | Apache-2.0 | A | 134 | Claude Code, Codex |
| azd-deploymentsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 29 | Claude Code |
| cdf-orchestration-setupNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 105 | Codex |
| langbot-deploylangbot-app/LangBot | Skill | 19k | today | Apache-2.0 | B | 104 | Claude Code, Codex |
| compute-env-setupUnicomAI/wanwu | Skill | 2.4k | yesterday | Apache-2.0 | A | 134 | Claude Code, Codex |
| compute-env-setupcompanion-inc/feynman | Skill | 10k | 7d ago | MIT | A | 45 | Claude Code, Codex |