Kubernetes and OpenShift

What is Kubernetes MCP Server?

Kubernetes MCP Server is a native Go-based implementation of the Model Context Protocol (MCP) for Kubernetes and OpenShift. Unlike other implementations, it directly interacts with the Kubernetes API server, eliminating the need for external dependencies like kubectl or helm command-line tools.

How to use Kubernetes MCP Server?

Kubernetes MCP Server can be used in various environments:

• Claude Desktop: Add the MCP server to your claude_desktop_config.json using npx.
• VS Code / VS Code Insiders: Install the Kubernetes MCP server extension directly from the marketplace or manually via the command line.
• Goose CLI: Configure the MCP server in your goose config.yaml using npm.

The server can also be configured using command-line arguments, allowing for customization of HTTP/SSE ports, logging levels, kubeconfig paths, and read-only/destructive operation modes.

Key Features of Kubernetes MCP Server

• Configuration Management: Automatically detects and updates changes in Kubernetes configuration, allowing viewing and management of .kube/config or in-cluster configurations.
• Generic Kubernetes Resource Operations: Supports all CRUD operations (Create, Read, Update, Delete) on any Kubernetes or OpenShift resource.
• Pod-Specific Operations: Provides specialized tools for Pods, including listing, getting, deleting, showing logs, top for resource usage, exec into a container, and running container images.
• Namespace and Event Management: Lists Kubernetes Namespaces and views Kubernetes events.
• OpenShift Project Management: Lists OpenShift Projects.
• Helm Integration: Allows installing, listing, and uninstalling Helm charts and releases.
• Native Go Implementation: Directly interacts with the Kubernetes API, ensuring high performance and low latency without external dependencies.
• Lightweight and Cross-Platform: Distributed as a single native binary for Linux, macOS, and Windows, and available as npm, Python packages, and Docker images.
• Configurable: Supports command-line arguments for server behavior customization.
• Well-tested: Extensive test suite for reliability across different Kubernetes environments.

Use Cases of Kubernetes MCP Server

• Automated Diagnosis and Fixing: Used by tools like Claude Desktop to automatically diagnose and fix deployments in OpenShift.
• Development Workflow Integration: Seamlessly integrates with development environments like VS Code for tasks such as Vibe Coding and deploying applications to OpenShift.
• AI Agent Integration: Leveraged by AI agents like Goose CLI for interacting with Kubernetes clusters.
• Debugging and Inspection: Can be run in read-only mode to debug or inspect clusters without making changes.

FAQ from Kubernetes MCP Server

Q: Does Kubernetes MCP Server require kubectl or helm to be installed?

A: No, Kubernetes MCP Server is a native Go-based implementation that directly interacts with the Kubernetes API server, so it does not require kubectl or helm or any other external dependencies.

Q: Is Kubernetes MCP Server cross-platform?

A: Yes, it is available as a single native binary for Linux, macOS, and Windows, as well as an npm package, a Python package, and a container/Docker image.

Q: Can I run Kubernetes MCP Server in a read-only mode?

A: Yes, you can use the --read-only command-line argument to run the server in read-only mode, which prevents any write operations on the Kubernetes cluster. You can also use --disable-destructive to disable only destructive operations.

Kubernetes MCP Server

✨ Features | 🚀 Getting Started | 🎥 Demos | ⚙️ Configuration | 🛠️ Tools | 🧑‍💻 Development

https://github.com/user-attachments/assets/be2b67b3-fc1c-4d11-ae46-93deba8ed98e

✨ Features

A powerful and flexible Kubernetes Model Context Protocol (MCP) server implementation with support for Kubernetes and OpenShift.

• ✅ Configuration:
  • Automatically detect changes in the Kubernetes configuration and update the MCP server.
  • View and manage the current Kubernetes .kube/config or in-cluster configuration.
• ✅ Generic Kubernetes Resources: Perform operations on any Kubernetes or OpenShift resource.
  • Any CRUD operation (Create or Update, Get, List, Delete).
• ✅ Pods: Perform Pod-specific operations.
  • List pods in all namespaces or in a specific namespace.
  • Get a pod by name from the specified namespace.
  • Delete a pod by name from the specified namespace.
  • Show logs for a pod by name from the specified namespace.
  • Top gets resource usage metrics for all pods or a specific pod in the specified namespace.
  • Exec into a pod and run a command.
  • Run a container image in a pod and optionally expose it.
• ✅ Namespaces: List Kubernetes Namespaces.
• ✅ Events: View Kubernetes events in all namespaces or in a specific namespace.
• ✅ Projects: List OpenShift Projects.
• ☸️ Helm:
  • Install a Helm chart in the current or provided namespace.
  • List Helm releases in all namespaces or in a specific namespace.
  • Uninstall a Helm release in the current or provided namespace.

Unlike other Kubernetes MCP server implementations, this IS NOT just a wrapper around kubectl or helm command-line tools. It is a Go-based native implementation that interacts directly with the Kubernetes API server.

There is NO NEED for external dependencies or tools to be installed on the system. If you're using the native binaries you don't need to have Node or Python installed on your system.

• ✅ Lightweight: The server is distributed as a single native binary for Linux, macOS, and Windows.
• ✅ High-Performance / Low-Latency: Directly interacts with the Kubernetes API server without the overhead of calling and waiting for external commands.
• ✅ Cross-Platform: Available as a native binary for Linux, macOS, and Windows, as well as an npm package, a Python package, and container/Docker image.
• ✅ Configurable: Supports command-line arguments to configure the server behavior.
• ✅ Well tested: The server has an extensive test suite to ensure its reliability and correctness across different Kubernetes environments.

🚀 Getting Started

Requirements

• Access to a Kubernetes cluster.

Claude Desktop

Using npx

If you have npm installed, this is the fastest way to get started with kubernetes-mcp-server on Claude Desktop.

Open your claude_desktop_config.json and add the mcp server to the list of mcpServers:

{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": [
        "-y",
        "kubernetes-mcp-server@latest"
      ]
    }
  }
}

VS Code / VS Code Insiders

Install the Kubernetes MCP server extension in VS Code Insiders by pressing the following link:

Alternatively, you can install the extension manually by running the following command:

# For VS Code
code --add-mcp '{"name":"kubernetes","command":"npx","args":["kubernetes-mcp-server@latest"]}'
# For VS Code Insiders
code-insiders --add-mcp '{"name":"kubernetes","command":"npx","args":["kubernetes-mcp-server@latest"]}'

Goose CLI

Goose CLI is the easiest (and cheapest) way to get rolling with artificial intelligence (AI) agents.

Using npm

If you have npm installed, this is the fastest way to get started with kubernetes-mcp-server.

Open your goose config.yaml and add the mcp server to the list of mcpServers:

extensions:
  kubernetes:
    command: npx
    args:
      - -y
      - kubernetes-mcp-server@latest

🎥 Demos

Diagnosing and automatically fixing an OpenShift Deployment

Demo showcasing how Kubernetes MCP server is leveraged by Claude Desktop to automatically diagnose and fix a deployment in OpenShift without any user assistance.

https://github.com/user-attachments/assets/a576176d-a142-4c19-b9aa-a83dc4b8d941

Vibe Coding a simple game and deploying it to OpenShift

In this demo, I walk you through the process of Vibe Coding a simple game using VS Code and how to leverage Podman MCP server and Kubernetes MCP server to deploy it to OpenShift.

Supercharge GitHub Copilot with Kubernetes MCP Server in VS Code - One-Click Setup!

In this demo, I'll show you how to set up Kubernetes MCP server in VS code just by clicking a link.

⚙️ Configuration

The Kubernetes MCP server can be configured using command line (CLI) arguments.

You can run the CLI executable either by using npx, uvx, or by downloading the latest release binary.

# Run the Kubernetes MCP server using npx (in case you have npm and node installed)
npx kubernetes-mcp-server@latest --help

# Run the Kubernetes MCP server using uvx (in case you have uv and python installed)
uvx kubernetes-mcp-server@latest --help

# Run the Kubernetes MCP server using the latest release binary
./kubernetes-mcp-server --help

Configuration Options

Option	Description
--http-port	Starts the MCP server in Streamable HTTP mode and listens on the specified port (path /mcp). Deprecated: Please use --port.
--sse-port	Starts the MCP server in Server-Sent Event (SSE) mode and listens on the specified port (path /sse). Deprecated: Please use --port.
--log-level	Sets the logging level (values from 0-9). Similar to kubectl logging levels.
--kubeconfig	Path to the Kubernetes configuration file. If not provided, it will try to resolve the configuration (in-cluster, default location, etc.).
--list-output	Output format for resource list operations (one of: yaml, table) (default "table")
--read-only	If set, the MCP server will run in read-only mode, meaning it will not allow any write operations (create, update, delete) on the Kubernetes cluster. This is useful for debugging or inspecting the cluster without making changes.
--disable-destructive	If set, the MCP server will disable all destructive operations (delete, update, etc.) on the Kubernetes cluster. This is useful for debugging or inspecting the cluster without accidentally making changes. This option has no effect when --read-only is used.

🛠️ Tools

configuration_view

Get the current Kubernetes configuration content as a kubeconfig YAML

Parameters:

• minified (boolean, optional, default: true)
  • Return a minified version of the configuration
  • If true, keeps only the current-context and relevant configuration pieces
  • If false, returns all contexts, clusters, auth-infos, and users

events_list

List all the Kubernetes events in the current cluster from all namespaces

Parameters:

• namespace (string, optional)
  • Namespace to retrieve the events from. If not provided, will list events from all namespaces

helm_install

Install a Helm chart in the current or provided namespace with the provided name and chart

Parameters:

• chart (string, required)
  • Name of the Helm chart to install
  • Can be a local path or a remote URL
  • Example: ./my-chart.tgz or https://example.com/my-chart.tgz
• values (object, optional)
  • Values to pass to the Helm chart
  • Example: {"key": "value"}
• name (string, optional)
  • Name of the Helm release
  • Random name if not provided
• namespace (string, optional)
  • Namespace to install the Helm chart in
  • If not provided, will use the configured namespace

helm_list

List all the Helm releases in the current or provided namespace (or in all namespaces if specified)

Parameters:

• namespace (string, optional)
  • Namespace to list the Helm releases from
  • If not provided, will use the configured namespace
• all_namespaces (boolean, optional)
  • If true, will list Helm releases from all namespaces
  • If false, will list Helm releases from the specified namespace

helm_uninstall

Uninstall a Helm release in the current or provided namespace with the provided name

Parameters:

• name (string, required)
  • Name of the Helm release to uninstall
• namespace (string, optional)
  • Namespace to uninstall the Helm release from
  • If not provided, will use the configured namespace

namespaces_list

List all the Kubernetes namespaces in the current cluster

Parameters: None

pods_delete

Delete a Kubernetes Pod in the current or provided namespace with the provided name

Parameters:

• name (string, required)
  • Name of the Pod to delete
• namespace (string, required)
  • Namespace to delete the Pod from

pods_exec

Execute a command in a Kubernetes Pod in the current or provided namespace with the provided name and command

Parameters:

• command (string[], required)
  • Command to execute in the Pod container
  • First item is the command, rest are arguments
  • Example: ["ls", "-l", "/tmp"]
• name (string, required)
  • Name of the Pod
• namespace (string, required)
  • Namespace of the Pod
• container (string, optional)
  • Name of the Pod container to get logs from

pods_get

Get a Kubernetes Pod in the current or provided namespace with the provided name

Parameters:

• name (string, required)
  • Name of the Pod
• namespace (string, required)
  • Namespace to get the Pod from

pods_list

List all the Kubernetes pods in the current cluster from all namespaces

Parameters:

• labelSelector (string, optional)
  • Kubernetes label selector (e.g., 'app=myapp,env=prod' or 'app in (myapp,yourapp)'). Use this option to filter the pods by label

pods_list_in_namespace

List all the Kubernetes pods in the specified namespace in the current cluster

Parameters:

• namespace (string, required)
  • Namespace to list pods from
• labelSelector (string, optional)
  • Kubernetes label selector (e.g., 'app=myapp,env=prod' or 'app in (myapp,yourapp)'). Use this option to filter the pods by label

pods_log

Get the logs of a Kubernetes Pod in the current or provided namespace with the provided name

Parameters:

• name (string, required)
  • Name of the Pod to get logs from
• namespace (string, required)
  • Namespace to get the Pod logs from
• container (string, optional)
  • Name of the Pod container to get logs from

pods_run

Run a Kubernetes Pod in the current or provided namespace with the provided container image and optional name

Parameters:

• image (string, required)
  • Container Image to run in the Pod
• namespace (string, required)
  • Namespace to run the Pod in
• name (string, optional)
  • Name of the Pod (random name if not provided)
• port (number, optional)
  • TCP/IP port to expose from the Pod container
  • No port exposed if not provided

pods_top

Lists the resource consumption (CPU and memory) as recorded by the Kubernetes Metrics Server for the specified Kubernetes Pods in the all namespaces, the provided namespace, or the current namespace

Parameters:

• all_namespaces (boolean, optional, default: true)
  • If true, lists resource consumption for Pods in all namespaces
  • If false, lists resource consumption for Pods in the configured or provided namespace
• namespace (string, optional)
  • Namespace to list the Pod resources from
  • If not provided, will list Pods from the configured namespace (in case all_namespaces is false)
• name (string, optional)
  • Name of the Pod to get resource consumption from
  • If not provided, will list resource consumption for all Pods in the applicable namespace(s)
• label_selector (string, optional)
  • Kubernetes label selector (e.g. 'app=myapp,env=prod' or 'app in (myapp,yourapp)'), use this option when you want to filter the pods by label (Optional, only applicable when name is not provided)

projects_list

List all the OpenShift projects in the current cluster

resources_create_or_update

Create or update a Kubernetes resource in the current cluster by providing a YAML or JSON representation of the resource

Parameters:

• resource (string, required)
  • A JSON or YAML containing a representation of the Kubernetes resource
  • Should include top-level fields such as apiVersion, kind, metadata, and spec

Common apiVersion and kind include:

• v1 Pod
• v1 Service
• v1 Node
• apps/v1 Deployment
• networking.k8s.io/v1 Ingress

resources_delete

Delete a Kubernetes resource in the current cluster

Parameters:

• apiVersion (string, required)
  • apiVersion of the resource (e.g., v1, apps/v1, networking.k8s.io/v1)
• kind (string, required)
  • kind of the resource (e.g., Pod, Service, Deployment, Ingress)
• name (string, required)
  • Name of the resource
• namespace (string, optional)
  • Namespace to delete the namespaced resource from
  • Ignored for cluster-scoped resources
  • Uses configured namespace if not provided

resources_get

Get a Kubernetes resource in the current cluster

Parameters:

• apiVersion (string, required)
  • apiVersion of the resource (e.g., v1, apps/v1, networking.k8s.io/v1)
• kind (string, required)
  • kind of the resource (e.g., Pod, Service, Deployment, Ingress)
• name (string, required)
  • Name of the resource
• namespace (string, optional)
  • Namespace to retrieve the namespaced resource from
  • Ignored for cluster-scoped resources
  • Uses configured namespace if not provided

resources_list

List Kubernetes resources and objects in the current cluster

Parameters:

• apiVersion (string, required)
  • apiVersion of the resources (e.g., v1, apps/v1, networking.k8s.io/v1)
• kind (string, required)
  • kind of the resources (e.g., Pod, Service, Deployment, Ingress)
• namespace (string, optional)
  • Namespace to retrieve the namespaced resources from
  • Ignored for cluster-scoped resources
  • Lists resources from all namespaces if not provided
• labelSelector (string, optional)
  • Kubernetes label selector (e.g., 'app=myapp,env=prod' or 'app in (myapp,yourapp)'). Use this option to filter the pods by label.

🧑‍💻 Development

Running with mcp-inspector

Compile the project and run the Kubernetes MCP server with mcp-inspector to inspect the MCP server.

# Compile the project
make build
# Run the Kubernetes MCP server with mcp-inspector
npx @modelcontextprotocol/inspector@latest $(pwd)/kubernetes-mcp-server