Kai MCP Server

A Model Context Protocol (MCP) server for managing Kubernetes clusters from MCP-compatible clients like Claude Desktop, Cursor, and Continue.

Local serverstdioGo

What is the Kai MCP server?

Kai MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A Model Context Protocol (MCP) server for managing Kubernetes clusters from MCP-compatible clients like Claude Desktop, Cursor, and Continue.

What you get

Kai exposes Kubernetes operations as MCP tools, letting an LLM client manage your cluster through natural language — workloads, networking, config, storage, RBAC, custom resources, and raw manifests.

What the assistant can call

Once Kai is connected, these are the calls the assistant has available:

  • Networking — The Networking tool exposed by this server
  • Configuration — The Configuration tool exposed by this server
  • Storage — The Storage tool exposed by this server
  • Security — The Security tool exposed by this server
  • Utilities — The Utilities tool exposed by this server
  • Advanced — The Advanced tool exposed by this server
  • Cursor — The Cursor tool exposed by this server
  • Continue — Add to your Continue configuration (~/.continue/config.json):

Configuration and credentials

The server connects to your current kubectl context by default. Ensure you have access to a Kubernetes cluster configured for kubectl (e.g., minikube, Rancher Desktop, kind, EKS, GKE, AKS).

Setting it up

cyclon/kai on a container image is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the file and storage access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Kai's toolset — Networking, Configuration, Storage and 5 more — is a fair guide to whether it matches your workflow. It is maintained by basebandit; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the kai mcp server does with a few real requests.

Available tools

ToolWhat it does
NetworkingThe Networking tool exposed by this server.
ConfigurationThe Configuration tool exposed by this server.
StorageThe Storage tool exposed by this server.
SecurityThe Security tool exposed by this server.
UtilitiesThe Utilities tool exposed by this server.
AdvancedThe Advanced tool exposed by this server.
CursorThe Cursor tool exposed by this server.
ContinueAdd to your Continue configuration (~/.continue/config.json):

How to install the Kai MCP server

Add the server configuration:

```json
{
  "mcpServers": {
    "kubernetes": {
      "command": "/path/to/kai"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

The server connects to your current kubectl context by default. Ensure you have access to a Kubernetes cluster configured for kubectl (e.g., minikube, Rancher Desktop, kind, EKS, GKE, AKS).

Example prompts to try

  • Use Kai to Networking.
  • Use Kai to Configuration.
  • Use Kai to Storage.

Frequently asked questions

It connects Kai to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (Networking, Configuration, Storage, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Kai directly.