A Model Context Protocol server for Kubernetes. It lets an MCP-capable client (Claude Desktop, Claude Code, etc.) inspect and operate Kubernetes clusters across multiple contexts — with behaviour…
mcp-kubernetes is an MCP project maintained in the dockndevai/mcp-kubernetes repository. The maintainer describes its purpose as “A Model Context Protocol server for Kubernetes. It lets an MCP-capable client (Claude Desktop, Claude Code, etc.) inspect and operate Kubernetes clusters across multiple contexts…”. Read the project documentation for the complete scope.
The documented npm package is @dockndevai/mcp-kubernetes. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares KUBECONFIG_PATH, K8S_MODE. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"kubernetes": {
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-kubernetes"
],
"env": {
"KUBECONFIG_PATH": "/Users/you/.kube/config",
"K8S_MODE": "read-only"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| KUBECONFIG_PATH | Declared in the maintainer’s client configuration. | Check documentation |
| K8S_MODE | Declared in the maintainer’s client configuration. | Check documentation |
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.