Kubernetes Multi-Cluster Manager MCP server

This MCP server provides a gateway for Generative AI systems to interact with multiple Kubernetes clusters using the Model Context Protocol (MCP). It enables operations across Kubernetes resources and simplifies multi-cluster management through a unified interface.

Installation

The Multi-Cluster MCP Server can be easily installed and configured to work with your Kubernetes environments.

Prerequisites

• Ensure kubectl is installed on your system
• Set up your KUBECONFIG environment variable to access your cluster
• In multi-cluster setups, the configured cluster is treated as the hub cluster

Installation Options

Using the MCP Inspector for Development

mcp dev ./src/multicluster_mcp_server/__main__.py 

Using the Package Manager

You can install the server using the uvx package manager:

uvx multicluster-mcp-server@latest

Configuration

Server Configuration

To configure the MCP server in your environment, use the following JSON configuration:

{
  "mcpServers": {
    "multicluster-mcp-server": {
      "command": "uvx",
      "args": [
        "multicluster-mcp-server@latest"
      ]
    }
  }
}

Usage

The Multi-Cluster MCP Server provides several key features for interacting with Kubernetes clusters:

Kubernetes Cluster Operations

The server supports the following operations:

• Retrieve resources from the hub cluster (current context)
• Retrieve resources from managed clusters
• Connect to managed clusters using specified ClusterRoles
• Access resources across multiple Kubernetes clusters via Open Cluster Management

Example Commands

While specific commands depend on your client implementation, the server facilitates operations like:

• Retrieving pod information across multiple clusters
• Managing cluster policies
• Monitoring cluster health
• Accessing cluster resources through a unified interface

Connecting to Managed Clusters

To connect to a managed cluster, you'll need to specify the appropriate ClusterRole through your MCP client. The server handles the authentication and access control, allowing you to seamlessly interact with resources across your cluster ecosystem.

Future Capabilities

The server is being developed to include additional features:

• Resource metrics, logs, and alerts retrieval
• Prompt templates for Open Cluster Management
• Integration with more Kubernetes resource types

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.