k8s-mcp
用于集群诊断的Kubernetes MCP服务器. k8s-mcp is a Model Context Protocol (MCP) server maintained by vlttnv. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 12 tools, including get_namespaces, list_pods, failed_pods, pending_pods, high_restart_pods, list_nodes, node_capacity and list_deployments, that an agent can call directly. It is categorized under DevOps/Kubernetes and Integration/Claude.
什么是MCP
这是一个专为Kubernetes集群设计的只读型模型上下文协议服务器。它提供全面的API来获取集群信息和诊断问题，使AI助手能够理解并与Kubernetes环境交互。
如何使用MCP
该MCP服务器可通过Python 3.8+在本地安装，并通过kubeconfig或集群内配置连接到Kubernetes集群。它通过配置文件与Claude AI集成，允许用户通过自然语言提示查询集群信息。
MCP的用途
该MCP支持AI辅助的Kubernetes集群管理，包括监控集群健康状况、调试问题、检查资源和管理部署。它可以回答有关pod、节点、服务和部署的问题，并帮助识别和排查常见的Kubernetes问题。
AIMCP authority
DR and traffic signal for the AIMCP public domain.
Frequently asked questions
What is the k8s-mcp MCP server?
k8s-mcp is a Model Context Protocol server from vlttnv. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.
How do I connect k8s-mcp to my AI client?
Add k8s-mcp to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.
What tools does k8s-mcp provide?
k8s-mcp provides 12 tools: get_namespaces, list_pods, failed_pods, pending_pods, high_restart_pods, list_nodes, node_capacity, list_deployments, list_services, list_events, orphaned_resources and get_resource_yaml.
Is k8s-mcp free to use?
k8s-mcp is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.
Vernclaw Plugins for OpenClaw
Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.