Provides a gateway for Generative AI systems to interact with multiple Kubernetes clusters through the Model Context Protocol, enabling comprehensive Kubernetes resource operations and simplified multi-cluster infrastructure management.

Installation

NPX

npx -y multicluster-mcp-server@latest

Configuration

MCP Server Configuration

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

Available Tools

Tool	Description
retrieve_hub_cluster_resources	Retrieve resources from the hub cluster (current context)
retrieve_managed_cluster_resources	Retrieve resources from managed clusters
connect_to_managed_cluster	Connect to a managed cluster using the specified ClusterRole
access_multi_cluster_resources	Access resources across multiple Kubernetes clusters via Open Cluster Management
retrieve_metrics_logs_alerts	Retrieve and analyze metrics, logs, and alerts from integrated clusters

Capabilities

• Retrieve resources from the hub cluster (current context)
• Retrieve resources from managed clusters
• Connect to a managed cluster using the specified ClusterRole
• Access resources across multiple Kubernetes clusters via Open Cluster Management
• Retrieve and analyze metrics, logs, and alerts from integrated clusters
• Comprehensive Kubernetes resource operations
• Simplified multi-cluster infrastructure management
• Interactive cluster monitoring

Environment Variables

Optional

• KUBECONFIG - Used to access cluster configuration, treats the configured cluster as a hub cluster in a multi-cluster setup

Notes

Ensure that kubectl is installed. By default, the tool uses the KUBECONFIG environment variable to access the cluster. In a multi-cluster configuration, it treats the configured cluster as a hub cluster, accessing others through it. Prompt templates and MCP resources for Open Cluster Management are currently in the planning stage.