The Kubernetes Model Context Protocol (MCP) Server provides a native Go-based implementation for interacting with Kubernetes and OpenShift clusters. Unlike many alternatives, it avoids wrapping `kubectl` or `helm` command-line tools, opting for direct interaction with the Kubernetes API server to deliver high performance and low latency. The current stable version is `0.0.60`. Release cadence is frequent, indicating active development. Key features include automatic configuration updates, comprehensive CRUD operations on generic Kubernetes resources, Pod-specific operations (logs, exec, top), Namespace and Event management, OpenShift Project listing, and full Helm chart management (install, list, uninstall). It supports multi-cluster environments via `kubeconfig` and integrates optional OpenTelemetry distributed tracing and metrics. The server is distributed as a single native binary for various operating systems (Linux, macOS, Windows), an npm package (which is a wrapper for the binary), a Python package, and a Docker image, requiring no external dependencies like Node.js or Python on the host system when using the native binary.
npm install kubernetes-mcp-serverNo compatibility data collected yet for this library.
This quickstart demonstrates how to launch the Kubernetes MCP Server as a background process using `npx`, configuring its port and a specific flag, and hinting at API interaction.
Update your custom code calling `provider.GetTargets` to accommodate the new signature, which now accepts an optional user-scoping parameter.
If this new multi-cluster behavior breaks your current setup, disable the feature by providing the `--disable-multi-cluster` CLI flag when starting the server, or by setting a specific `cluster_provider_strategy` in your Kubernetes MCP server's TOML configuration.
Understand that interaction with the server is typically via CLI commands (e.g., `npx kubernetes-mcp-server`) to start it, and then by making HTTP requests to the running server's API endpoints, rather than importing JavaScript modules and calling functions directly.
Install the package globally using `npm install -g kubernetes-mcp-server`, or execute it directly with `npx kubernetes-mcp-server` to leverage the local `node_modules` executable.
Ensure the server process is actively running. Check its startup logs for the actual listening address and port, or explicitly specify them using the `--port` and `--bind-address` flags when launching the server (e.g., `npx kubernetes-mcp-server --port 8081`).
Provide a `kubeconfig` file with the necessary RBAC permissions for the server to operate. Verify your `KUBECONFIG` environment variable is correctly set, or ensure the server is running within a Kubernetes cluster with a service account that has been granted appropriate roles.
No dependency data recorded yet.