开发者工具 · 云平台

Kubernetes MCP Server logo

Kubernetes MCP Server

manusa/kubernetes-mcp-server

Kubernetes MCP服务器是一个强大的Kubernetes模型上下文协议实现,支持Kubernetes和OpenShift集群操作,无需依赖外部工具即可执行各种资源管理任务。

安装

npx -y kubernetes-mcp-server@latest

客户端配置

{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": [
        "-y",
        "kubernetes-mcp-server@latest"
      ]
    }
  }
}
GitHub 星标
135
作者
@manusa
分类
开发者工具, 云平台
更新于
2026年10月6日

工具(40)

  • configuration_view

    Get the current Kubernetes configuration content as a kubeconfig YAML

  • nodes_log

    Get logs from a Kubernetes node (kubelet, kube-proxy, or other system logs).

  • nodes_stats_summary

    Get detailed resource usage statistics from a Kubernetes node via the kubelet's Summary API.

  • pods_get

    Get a Kubernetes Pod in the current or provided namespace with the provided name

  • pods_delete

    Delete a Kubernetes Pod in the current or provided namespace with the provided name

  • pods_exec

    Execute a command in a Kubernetes Pod (shell access, run commands in container) in the current or provided namespace with the provided name and command

  • pods_log

    Get the logs of a Kubernetes Pod in the current or provided namespace with the provided name

  • pods_run

    Run a Kubernetes Pod in the current or provided namespace with the provided container image and optional name

  • resources_get

    Get a Kubernetes resource in the current cluster by providing its apiVersion, kind, optionally the namespace, and its name (common apiVersion and kind include:…

  • resources_create_or_update

    Create or update a Kubernetes resource via Server-Side Apply.

  • resources_delete

    Delete a Kubernetes resource in the current cluster by providing its apiVersion, kind, optionally the namespace, and its name (common apiVersion and kind…

  • resources_scale

    Get or update the scale of a Kubernetes resource in the current cluster by providing its apiVersion, kind, name, and optionally the namespace.

  • helm_install

    Install (deploy) a Helm chart to create a release in the current or provided namespace

  • helm_uninstall

    Uninstall a Helm release in the current or provided namespace

  • kcp_workspace_describe

    Get detailed information about a specific kcp workspace

  • kiali_get_mesh_traffic_graph

    Returns service-to-service traffic topology, dependencies, and network metrics (throughput, response time, mTLS) for the specified namespaces.

  • kiali_get_mesh_status

    Retrieves the high-level health, topology, and environment details of the Istio service mesh.

  • kiali_manage_istio_config_read

    Read Istio, Gateway API, and Inference API config. 'list' groups by namespace→'group/version/kind'→{valid:[...],invalid:[...]} where valid/invalid arrays…

  • kiali_manage_istio_config

    Create, patch, or delete Istio, Gateway API, and Inference API config.

  • kiali_list_mesh_clusters

    Returns the list of Istio mesh clusters that Kiali can access.

  • kiali_get_resource_details

    Fetches a list of resources OR retrieves detailed data for a specific resource.

  • kiali_list_traces

    Lists distributed traces for a service in a namespace.

  • kiali_get_trace_details

    Fetches a single distributed trace by trace_id and returns its call hierarchy (service tree with duration, status, and nested calls).

  • kiali_get_pod_performance

    Returns a human-readable text summary with current Pod CPU/memory usage (from Prometheus) compared to Kubernetes requests/limits (from the Pod spec).

  • kiali_get_logs

    Get the logs of a Kubernetes Pod (or workload name that will be resolved to a pod) in a namespace.

  • kiali_get_metrics

    Returns a compact JSON summary of Istio metrics (latency quantiles, traffic trends, throughput, payload sizes) for the given resource.

  • vm_clone

    Clone a VirtualMachine on KubeVirt by creating a VirtualMachineClone resource.

  • vm_console_screenshot

    Capture a screenshot of the graphical (VNC) console of a VirtualMachine on KubeVirt as a PNG image.

  • vm_create

    Create a VirtualMachine on KubeVirt with the specified configuration, automatically resolving instance types, preferences, and container disk images.

  • vm_guest_info

    Get guest operating system information from a VirtualMachine's QEMU guest agent.

  • vm_lifecycle

    Manage KubeVirt VirtualMachine lifecycle: start, stop, restart, pause, or unpause a VM

  • vm_create_from_template

    Create a VirtualMachine from a VirtualMachineTemplate (virt-template) on KubeVirt.

  • vm_troubleshoot

    Diagnose KubeVirt VirtualMachine issues with automated root-cause detection.

  • netobserv_list_flows

    Lists NetObserv network flow records from Loki.

  • netobserv_get_flow_metrics

    Returns aggregated NetObserv flow metrics as topology or time-series data.

  • netobserv_export_flows

    Exports NetObserv flow records as CSV with the same filters as list_flows.

  • tekton_pipeline_start

    Start a Tekton Pipeline by creating a PipelineRun that references it

  • tekton_pipelinerun_lifecycle

    Manage a Tekton PipelineRun lifecycle by restarting it with the same spec or cancelling it by setting spec.status to Cancelled.

  • tekton_pipelinerun_logs

    Get logs for all TaskRuns owned by a Tekton PipelineRun.

  • tekton_task_start

    Start a Tekton Task by creating a TaskRun that references it

本页信息摘自该项目的 README。 查看 README

支持的客户端

该服务器 README 中提到的客户端:

查看全部
Claude Desktop logo

Claude Desktop

桌面端 · 免费增值 · Proprietary

Anthropic 官方推出的 Claude AI 桌面应用程序。支持 MCP 服务器以扩展功能。

WindowsMacOS
Cursor logo

Cursor

桌面端 · 免费增值 · Proprietary

首个代理式 IDE。Cursor 编辑器让开发者与 AI 的工作真正融合在一起,提供如魔法般的编码体验。

WindowsMacOSLinux
VS Code GitHub Copilot logo

VS Code GitHub Copilot

桌面端 · 免费增值 · MIT

VS Code 通过代理模式将 MCP 与 GitHub Copilot 集成,允许在你的代理编码工作流中直接与 MCP 提供的工具交互。在 Claude Desktop、工作区或用户设置中配置服务器,提供引导式 MCP 安装和安全处理输入变量中的密钥,避免泄露硬编码密钥。

WindowsMacOSLinuxWeb
Goose logo

Goose

桌面端 · 免费 · Apache 2.0

通用 AI 代理,可以动态插入新扩展并学习如何使用它们。它使用来自多个扩展的工具解决更高级的问题,可以同时与多个扩展交互。

MacOSLinux

相关 MCP 服务器

更多服务器
Playwright logo

Playwright

microsoft/playwright

72.2k

Playwright是一个跨浏览器的Web测试和自动化框架,支持Chromium、Firefox和WebKit,提供无头执行、多浏览器兼容性测试、强大的断言和工具支持,适用于多种编程语言。

开发者工具
repomix logo

repomix

yamadashy/repomix

15.2k

Repomix是一个将代码库打包为AI友好格式的工具,支持本地和远程仓库处理,提供代码压缩、安全检查和多种输出格式。

开发者工具
UI-TARS-desktop logo

UI-TARS-desktop

bytedance/UI-TARS-desktop

12.9k

TARS 是字节跳动的多模态 AI 智能体技术栈,包含两个项目:Agent TARS(基于 MCP 的命令行与 Web UI 智能体)和 UI-TARS-desktop(桌面 GUI 智能体)。

开发者工具
blender logo

blender

ahujasid/blender-mcp

10.6k

BlenderMCP通过MCP协议将Blender与Claude AI连接,实现AI辅助3D建模与场景控制

开发者工具
Playwright Browser Automation logo

Playwright Browser Automation

microsoft/playwright-mcp

9.2k

Playwright MCP是一个基于Playwright的浏览器自动化服务器,通过结构化数据而非像素输入实现LLM与网页的交互。

开发者工具
2344 logo

2344

comet-ml/opik

7k

Opik是一个开源的LLM评估框架,支持追踪、评估和监控LLM应用,帮助开发者构建更高效、更经济的LLM系统。

开发者工具