A Model Context Protocol (MCP) server for managing Kubernetes clusters through LLM clients like Claude and Ollama.
Kai provides a bridge between large language models (LLMs) and your Kubernetes clusters, enabling natural language interaction with Kubernetes resources. The server exposes a comprehensive set of tools for managing clusters, namespaces, pods, deployments, services, and other Kubernetes resources.
- Pods - Create, list, get, delete, and stream logs
- Deployments - Create, list, describe, and update
- Jobs - Batch workload management (create, get, list, delete)
- CronJobs - Scheduled batch workloads (create, get, list, delete)
- Services - Create, get, list, and delete
- Ingress - HTTP/HTTPS routing, TLS configuration (create, get, list, update, delete)
- ConfigMaps - Configuration management (create, get, list, update, delete)
- Secrets - Secret management (create, get, list, update, delete)
- Namespaces - Namespace management (create, get, list, delete)
- Context Management - Switch contexts, list contexts, rename, delete
- Nodes - Node monitoring, cordoning, and draining
- Cluster Health - Cluster status and resource metrics
- Persistent Volumes - PV and PVC management
- Storage Classes - Storage class operations
- RBAC - Roles, RoleBindings, and ServiceAccounts
- Port Forwarding - Forward ports to pods and services (start, stop, list sessions)
- Custom Resources - CRD and custom resource operations
- Events - Event streaming and filtering
- API Discovery - API resource exploration
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).
go install github.com/basebandit/kai/cmd/kai@latestkai [options]
Options:
-kubeconfig string Path to kubeconfig file (default "~/.kube/config")
-context string Name for the loaded context (default "local")
-transport string Transport mode: stdio (default) or sse
-sse-addr string Address for SSE server (default ":8080")
-log-format string Log format: json (default) or text
-log-level string Log level: debug, info, warn, error (default "info")
-version Show version information
Logs are written to stderr in structured JSON format by default, making them easy to parse:
{"time":"2024-01-15T10:30:00Z","level":"INFO","msg":"kubeconfig loaded","path":"/home/user/.kube/config","context":"local"}
{"time":"2024-01-15T10:30:00Z","level":"INFO","msg":"starting server","transport":"stdio"}Edit your Claude Desktop configuration:
# macOS
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
# Linux
code ~/.config/Claude/claude_desktop_config.jsonAdd the server configuration:
{
"mcpServers": {
"kubernetes": {
"command": "/path/to/kai"
}
}
}With custom kubeconfig:
{
"mcpServers": {
"kubernetes": {
"command": "/path/to/kai",
"args": ["-kubeconfig", "/path/to/custom/kubeconfig"]
}
}
}Add to your Cursor MCP settings:
{
"mcpServers": {
"kubernetes": {
"command": "/path/to/kai"
}
}
}Add to your Continue configuration (~/.continue/config.json):
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "/path/to/kai"
}
}
]
}
}For web-based clients or custom integrations, run in SSE mode:
kai -transport=sse -sse-addr=:8080Then connect to http://localhost:8080/sse.
By default, Kai uses ~/.kube/config. You can specify a different kubeconfig:
kai -kubeconfig=/path/to/custom/kubeconfig -context=my-clusterOnce configured, you can interact with your cluster using natural language:
- "List all pods in the default namespace"
- "Create a deployment named nginx with 3 replicas using the nginx:latest image"
- "Show me the logs for pod my-app"
- "Delete the service named backend"
- "Create a cronjob that runs every 5 minutes"
- "Create an ingress for my-app with TLS enabled"
- "Port forward service nginx on port 8080:80"
Contributions are welcome! Please see our contributing guidelines for more information.
This project is licensed under the MIT License.

