Multicluster MCP Server

🚀 Multi-Cluster MCP Server

The Multi-Cluster MCP Server provides a powerful gateway for Generative AI (GenAI) systems to interact with multiple Kubernetes clusters through the Model Context Protocol (MCP). It supports comprehensive Kubernetes resource operations, simplified multi-cluster management, and real-time cluster observability.

🚀 Quick Start

The Multi-Cluster MCP Server allows GenAI systems to communicate with multiple Kubernetes clusters. Here's how you can get started with it.

✨ Features

🛠️ MCP Tools - Kubernetes Cluster Awareness

• ✓ Retrieve resources from the hub cluster (current context).
• ✓ Retrieve resources from managed clusters.
• ✓ Connect to a managed cluster using a specified ClusterRole.
• ✓ Access resources across multiple Kubernetes clusters (via Open Cluster Management).
• ✗ Retrieve and analyze metrics, logs, and alerts in integrated clusters.
• ✗ Interact with multi-cluster APIs, including managed clusters, policies, add-ons, etc.

📦 Reusable Prompt Templates for Open Cluster Management (Planned)

• Provide reusable prompt templates for OCM tasks to simplify agent interaction and automation.

📚 MCP Resources for Open Cluster Management (Planned)

• Reference official OCM documentation and related resources to support development and integration.

💻 Usage Examples

Basic Usage

Use the following code snippet to configure the server:

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

⚠️ Important Note

Ensure that kubectl is installed. By default, this tool uses the KUBECONFIG environment variable to access clusters. In a multi-cluster environment, it treats the configured cluster as the hub cluster and accesses other clusters through it.

📄 License

This project is licensed under the MIT License.