mcp-kubernetes

MCP运维云端

提供方 Azure

运维云端 stdio · 本地进程 会话登录 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes

一句话选型结论

按资料字段整理

mcp-kubernetes 属于运维云端类 MCP 服务器,stdio · 本地进程,会话登录,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类运维云端 传输方式stdio · 本地进程 鉴权会话登录 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

运维云端
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

kubernetesmodel context protocolmcp server

安装与配置

stdio · 本地进程 会话登录
客户端在本机拉起子进程,数据不出本机
docker run -i --rm --mount type=bind,src=/home/username/.kube/config,dst=/home/mcp/.kube/config ghcr.io/azure/mcp-kubernetes

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 go,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
云资源查询

查实例、存储、账单等云上资源状态。

部署与发布

把部署、重启、回滚这类操作接进对话。

监控与告警

拉取监控指标,异常时让模型帮你判断。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好会话登录对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在运维云端场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
mcp-kubernetes当前 未标注 stdio · 本地进程 本地部署 有 未标注
lobehub 未标注 stdio · 本地进程 本地部署 有 2026-04-11
TrendRadar 未标注 stdio · 本地进程 本地部署 有 2026-04-13
Ui Tars Desktop 8a825770 未标注 stdio · 本地进程 本地部署 有 2026-05-17
ruflo 未标注 stdio · 本地进程 本地部署 有 2026-04-13
FastGPT 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

运维云端
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Azure上游标注的维护方 Azure
分类运维云端本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式会话登录远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · go本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

12.5 KB
来自项目仓库与上游目录的原文,未做删改

mcp-kubernetes

The mcp-kubernetes is a Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning the results in a format the AI tools can understand.

It allows AI tools to:

  • Query Kubernetes resources
  • Execute kubectl commands
  • Manage Kubernetes clusters through natural language interactions
  • Diagnose and interpret the states of Kubernetes resources

How it works

How to install

Container images are no longer produced or supported. Install a released binary locally and configure your MCP client to run it as a stdio subprocess.

Local

Install kubectl

Install kubectl if it's not installed yet and add it to your PATH, e.g.```bash

For Linux

curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"

For MacOS

curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/darwin/arm64/kubectl"


Install helm

Install helm if it's not installed yet and add it to your PATH, e.g.```bash
curl -sSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash

Config your MCP servers in Claude Desktop, Cursor, ChatGPT Copilot, Github Copilot and other supported AI clients, e.g.```json
{
"mcpServers": {
"kubernetes": {
"command": "<path of binary 'mcp-kubernetes'>",
"args": ["--transport", "stdio"],
"env": {
"KUBECONFIG": "<your-kubeconfig-path>"
}
}
}
}


### Options

Environment variables:

- `KUBECONFIG`: Path to your kubeconfig file, e.g. `/home//.kube/config`.
- `USE_LEGACY_TOOLS`: Set to `true` to use multiple specialized kubectl tools instead of the unified `call_kubectl` tool (default: `false`).

Command line arguments:```sh
Usage of ./mcp-kubernetes:
      --access-level string       Access level (readonly, readwrite, or admin) (default &quot;readonly&quot;)
      --additional-tools string   Comma-separated list of additional tools to support (kubectl is always enabled). Available: helm,cilium,hubble
      --allow-namespaces string   Comma-separated list of namespaces to allow (empty means all allowed)
      --otlp-endpoint string      OTLP endpoint for OpenTelemetry traces (e.g. localhost:4317, default &quot;&quot;)
      --timeout int               Timeout for command execution in seconds, default is 60s (default 60)
      --transport string          Transport mechanism to use (stdio only) (default &quot;stdio&quot;)

Unified vs Legacy Tools

By default, mcp-kubernetes uses a single unified call_kubectl tool that consolidates all kubectl operations into one tool interface. This significantly reduces context consumption while maintaining full functionality.

To use the legacy mode with multiple specialized tools (6-7 separate tools), set the environment variable:```json
{
"mcpServers": {
"kubernetes": {
"command": "mcp-kubernetes",
"env": {
"USE_LEGACY_TOOLS": "true"
}
}
}
}


### Access Levels

The `--access-level` flag controls what operations are allowed:

- **`readonly`** (default): Only read operations are allowed (get, describe, logs, etc.)
- **`readwrite`**: Read and write operations are allowed (create, delete, apply, etc.)
- **`admin`**: All operations are allowed, including admin operations (cordon, drain, taint, etc.)

Tools and operations are filtered at registration time based on the access level, so AI assistants only see operations they can actually use.

Example configurations:```json
// Read-only access (default)
{
  &quot;mcpServers&quot;: {
    &quot;kubernetes&quot;: {
      &quot;command&quot;: &quot;mcp-kubernetes&quot;
    }
  }
}

// Read-write access
{
  &quot;mcpServers&quot;: {
    &quot;kubernetes&quot;: {
      &quot;command&quot;: &quot;mcp-kubernetes&quot;,
      &quot;args&quot;: [&quot;--access-level&quot;, &quot;readwrite&quot;]
    }
  }
}

// Admin access
{
  &quot;mcpServers&quot;: {
    &quot;kubernetes&quot;: {
      &quot;command&quot;: &quot;mcp-kubernetes&quot;,
      &quot;args&quot;: [&quot;--access-level&quot;, &quot;admin&quot;]
    }
  }
}

Usage

Ask any questions about Kubernetes cluster in your AI client. The MCP tools make it easier for AI assistants to understand and use kubectl operations.

Example Queries```txt

What is the status of my Kubernetes cluster?

What is wrong with my nginx pod?

Show me all deployments in the production namespace

Scale my web deployment to 5 replicas

Check if I have permission to create pods

What is my current kubectl context?

List all available kubectl contexts

Switch to the production context


## Available Tools

### Unified Tool (Default)

By default, mcp-kubernetes uses a single unified `call_kubectl` tool that handles all kubectl operations. This approach significantly reduces context consumption compared to the legacy multi-tool approach.

**call_kubectl** - Execute kubectl commands
- **Available in**: All access levels (operations filtered by access level)
- **Parameters**:
  - `command`: The full kubectl command to execute including &#x27;kubectl&#x27; prefix (e.g., &quot;kubectl get pods -n default&quot;, &quot;kubectl apply -f deployment.yaml&quot;)
- **Examples**:```bash
  # Get pods
  command: &quot;kubectl get pods -n default&quot;

  # Apply configuration
  command: &quot;kubectl apply -f deployment.yaml&quot;

  # Scale deployment
  command: &quot;kubectl scale deployment nginx --replicas=3&quot;
  ```

### Legacy Tools (Optional)

When `USE_LEGACY_TOOLS=true`, the mcp-kubernetes server provides multiple specialized kubectl tools that group related operations together. Tools are automatically filtered based on your access level.

#### Kubectl Tools

kubectl_resources - Manage Kubernetes resources

**Available in**: readonly, readwrite, admin

Handles CRUD operations on Kubernetes resources and node management. In readonly mode, only supports `get` and `describe` operations. Node operations (cordon, uncordon, drain, taint) are available in admin mode only.

**Parameters:**

- `operation`: The operation to perform (get, describe, create, delete, apply, patch, replace, cordon, uncordon, drain, taint)
- `resource`: The resource type (e.g., pods, deployments, services, nodes) or empty for file-based operations
- `args`: Additional arguments like resource names, namespaces, and flags

**Examples:**```bash
# Get all pods
operation: &quot;get&quot;
resource: &quot;pods&quot;
args: &quot;--all-namespaces&quot;

# Apply a configuration
operation: &quot;apply&quot;
resource: &quot;&quot;
args: &quot;-f deployment.yaml&quot;

# Drain a node (admin only)
operation: &quot;drain&quot;
resource: &quot;node&quot;
args: &quot;worker-1 --ignore-daemonsets&quot;

# Add a taint (admin only)
operation: &quot;taint&quot;
resource: &quot;nodes&quot;
args: &quot;worker-1 key=value:NoSchedule&quot;

kubectl_workloads - Manage workload deployments

Available in: readwrite, admin

Manages deployment lifecycle operations including scaling and rollouts.

Parameters:

  • operation: The operation to perform (run, expose, scale, autoscale, rollout)
  • resource: For rollout operations, the subcommand (status, history, undo, restart, pause, resume)
  • args: Additional arguments

Examples:```bash

Scale a deployment

operation: "scale"
resource: "deployment"
args: "nginx --replicas=3"

Check rollout status

operation: "rollout"
resource: "status"
args: "deployment/nginx"


kubectl_metadata - Manage resource metadata

**Available in**: readwrite, admin

Updates labels, annotations, and other metadata on resources.

**Parameters:**

- `operation`: The operation to perform (label, annotate, set)
- `resource`: The resource type
- `args`: Resource name and metadata changes

**Examples:**```bash
# Add a label
operation: &quot;label&quot;
resource: &quot;pods&quot;
args: &quot;nginx-pod app=web&quot;

# Set image
operation: &quot;set&quot;
resource: &quot;image&quot;
args: &quot;deployment/nginx nginx=nginx:latest&quot;

kubectl_diagnostics - Debug and monitor resources

Available in: readonly, readwrite, admin

Provides debugging and monitoring capabilities.

Parameters:

  • operation: The operation to perform (logs, events, top, exec, cp)
  • resource: The resource type or specific resource
  • args: Additional arguments

Examples:```bash

View logs

operation: "logs"
resource: ""
args: "nginx-pod -f"

Execute command in pod

operation: "exec"
resource: ""
args: "nginx-pod -- ls /app"


kubectl_cluster - View cluster information

**Available in**: readonly, readwrite, admin

Provides cluster-level information and API discovery.

**Parameters:**

- `operation`: The operation to perform (cluster-info, api-resources, api-versions, explain)
- `resource`: For explain operation, the resource to document
- `args`: Additional flags

**Examples:**```bash
# Get cluster info
operation: &quot;cluster-info&quot;
resource: &quot;&quot;
args: &quot;&quot;

# Explain pod spec
operation: &quot;explain&quot;
resource: &quot;pod.spec&quot;
args: &quot;--recursive&quot;

kubectl_config - Configuration and security

Available in: readonly, readwrite, admin

Handles configuration validation, security operations, and kubectl context management. In readonly mode, supports diff, auth can-i, and read-only config operations.

Parameters:

  • operation: The operation to perform (diff, auth, certificate, config)
  • resource: Subcommand for auth/certificate/config operations
  • args: Operation-specific arguments

Examples:```bash

Check permissions

operation: "auth"
resource: "can-i"
args: "create pods"

Approve certificate

operation: "certificate"
resource: "approve"
args: "csr-name"

Get current context

operation: "config"
resource: "current-context"
args: ""

List all contexts

operation: "config"
resource: "get-contexts"
args: ""

Switch context (readwrite/admin only)

operation: "config"
resource: "use-context"
args: "my-cluster-context"


**Config Operations:**
- `current-context`: Display the current context (readonly, readwrite, admin)
- `get-contexts`: List all available contexts (readonly, readwrite, admin)
- `use-context`: Switch to a different context (readwrite, admin only)

#### Additional Tools

call_helm - Helm package manager

**Available when**: `--additional-tools=helm` is specified

Run Helm commands for managing Kubernetes applications.

**Parameters:**

- `command`: The helm command to execute

**Example:**```bash
command: &quot;list --all-namespaces&quot;

call_cilium - Cilium CNI commands

Available when: --additional-tools=cilium is specified

Run Cilium commands for network policies and observability.

Parameters:

  • command: The cilium command to execute

Example:```bash
command: "status"


call_hubble - Hubble observability commands

**Available when**: `--additional-tools=hubble` is specified

Run Hubble commands for network monitoring and debugging in Cilium-enabled clusters.

**Parameters:**

- `command`: The hubble command to execute

**Example:**```bash
command: &quot;status&quot;
command: &quot;observe observe --namespace backend-jobs  --from-label &#x27;app=web&#x27;&quot;
command: &quot;list nodes&quot;

Telemetry

Telemetry collection is on by default.

To opt out, set the environment variable KUBERNETES_MCP_COLLECT_TELEMETRY=false.

OpenTelemetry Support

The mcp-kubernetes server supports exporting telemetry data using OpenTelemetry Protocol (OTLP). You can configure an OTLP endpoint to send traces to any OpenTelemetry-compatible backend:```json
{
"mcpServers": {
"kubernetes": {
"command": "mcp-kubernetes",
"args": ["--otlp-endpoint", "localhost:4317"]
}
}
}


## Development

How to inspect MCP server requests and responses:```sh
npx @modelcontextprotocol/inspector &lt;path of binary &#x27;mcp-kubernetes&#x27;&gt;

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
mcp-kubernetes 怎么安装?

在客户端按下面的安装命令接入:docker run -i --rm --mount type=bind,src=/home/username/.kube/config,dst=/home/mcp/.kube/config ghcr.io/azure/mcp-kubernetes。装完在客户端配置里引用同一个包或端点。

mcp-kubernetes 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

mcp-kubernetes 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

mcp-kubernetes 需要 API Key 吗?

资料标注需要会话登录认证,使用前准备好对应凭据,并按最小权限配置。

mcp-kubernetes 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Gemini CLI、Codex;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

mcp-kubernetes 能提供哪些能力?

资料显示能力标签包括 kubernetes、model context protocol、mcp server。具体工具清单以官方文档为准。

mcp-kubernetes 需要什么运行环境?

运行时为 go;属于本地进程,需要在本机装好运行环境。

mcp-kubernetes 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。