"K3s" matching MCP servers:

Connects Claude Desktop to any Kubernetes cluster, enabling natural language queries for diagnostics and operations such as listing pods, viewing logs, scaling deployments, and more.

A read-only MCP server for inspecting Kubernetes clusters, allowing LLMs to list resources, describe pods, and read logs without mutation.

MCP server for managing Raspberry Pi K3s clusters via AI assistants like Claude Code.

Enables developers to manage Kubernetes workloads directly from their editor—listing pods, reading logs, scaling and restarting deployments, deleting pods, and applying configs—with secure authentication and no exposure of secret values.

An MCP server that provides complete Kubernetes API operations, enabling cluster management, resource CRUD, diagnostics, backup/restore, and multi-cluster configuration via natural language.

Enables Claude to run Kubernetes CLI tools (kubectl, istioctl, helm, argocd) in a secure, containerized environment via the Model Context Protocol.

This project is intended as a both MCP server connecting to Kubernetes and a library to build more servers for any custom resources in Kubernetes.

Enables LLMs like Claude to securely execute Kubernetes CLI tools (kubectl, helm, istioctl, argocd) across multiple clusters through dynamic kubeconfig support, allowing natural language Kubernetes management and operations.

An MCP server that lets AI assistants safely inspect and operate on Kubernetes clusters through natural conversation.

Enables natural language Kubernetes operations, including smart resource queries, pod root-cause analysis, cross-environment diffs, and manifest generation.

A lightweight MCP server that enables AI assistants to deploy, inspect, and operate Kubernetes workloads through high-level workflow tools, reducing token usage with structured outputs.

Enables LLMs to dynamically orchestrate containerized application deployments to a Kubernetes cluster, handling configuration validation, manifest generation, dry-run planning, and service endpoint extraction.

Enables spawning ephemeral Model Context Protocol (MCP) servers on Kubernetes using Server-Sent Events (SSE), supporting multiple runtimes.

Safe, read-only-by-default Kubernetes access for AI agents via MCP. Provides explicit readonly, readwrite, and dangerous permission modes, plus MCPB bundles for desktop clients.

Manage Your Kubernetes Cluster with k8s mcp-server

A read-only MCP server that gives Claude safe access to Kubernetes clusters, enabling listing, describing, and monitoring resources without mutation risks and with secret masking.

A Docker-based MCP server that enables Claude to run Kubernetes CLI tools (kubectl, istioctl, helm, argocd) in a secure containerized environment for managing and troubleshooting clusters.

Enables read-only interaction with a Kubernetes cluster, allowing listing of nodes, pods, deployments, and services, as well as fetching pod logs.

Enables interaction with Kubernetes clusters through 32 specialized tools for managing resources, deployments, and services. Provides both CLI and web interfaces for real-time Kubernetes operations powered by Google Gemini.

Provides read-only Kubernetes cluster operations via MCP, enabling LLMs to query nodes, pods, logs, events, and watch real-time status for troubleshooting.