What are the requirements for Kubernetes MCP Server?
Rust 1.70 or later, kubectl installed and configured, a Kubernetes cluster with appropriate permissions, and a configured kubeconfig.
@wasilak
基本信息
An experimental Model Context Protocol (MCP) server that exposes Kubernetes resources to AI chat interfaces.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
An experimental Model Context Protocol (MCP) server that exposes Kubernetes functionality to AI chat interfaces through kubectl, allowing AI assistants to analyze and manage cluster resources using familiar kubectl commands.
Install by cloning the repository and building with cargo build --release, then configure your AI assistant to use the server (instructions depend on your AI platform).
kubectl tool for executing any kubectl commandRust 1.70 or later, kubectl installed and configured, a Kubernetes cluster with appropriate permissions, and a configured kubeconfig.
It uses your default kubeconfig and kubectl installation.
Run with appropriate RBAC permissions, consider implementing command validation or whitelisting, monitor and audit command execution, and use it in a controlled environment.
The README describes it as experimental and a demonstration of how to integrate Kubernetes with AI assistants.
Yes, it provides a single `kubectl` tool that can execute any kubectl command, giving AI assistants full access to your cluster's capabilities.
A docker MCP Server (modelcontextprotocol)
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

Nippy is drag-and-drop hosting (nippy.host) with an MCP server: connect it and your assistant can publish HTML, folders of photos, or file downloads to a live *.nippy.site URL — and keep editing the site in place at the

Build and run websites, APIs, automations, and admin tools from chat. Your agent creates the data, logic, pages, and scheduled jobs; Tessryx hosts them on your own domain. No code generated, nothing to deploy.
评论