Multicluster MCP Server

What is Multicluster MCP Server about?

A gateway that lets Generative AI agents work across a hub Kubernetes cluster and its managed clusters, performing resource CRUD, fetching metrics, logs, and alerts through the Model Context Protocol.

How to use Multicluster MCP Server?

Ensure kubectl is installed and your KUBECONFIG points to the hub cluster.
Add the server configuration to your MCP client:

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

Run the server via the generated command (e.g., npx -y multicluster-mcp-server@latest).
Use MCP calls to retrieve resources, metrics, logs, or invoke multi‑cluster APIs.

Key features of Multicluster MCP Server

Retrieve resources from the hub cluster and any managed cluster.
Connect to a managed cluster with a specific ClusterRole.
Access metrics, logs, and alerts across clusters.
Unified interface for multi‑cluster APIs such as ManagedClusters, Policies, Add‑ons.
Reusable prompt templates and reference docs for Open Cluster Management tasks.

Use cases of Multicluster MCP Server

Automating troubleshooting by pulling logs/metrics from any cluster in a fleet.
Enabling GenAI agents to plan and execute OCM policies across clusters.
Building observability dashboards that aggregate data from hub and managed clusters.
Facilitating AI‑driven policy compliance checks in multi‑cluster environments.

FAQ

Q: Do I need any special permissions? A: Access to the hub cluster via kubectl is required; the server can use a ClusterRole you specify for managed clusters.

Q: Can I use this with non‑OpenShift clusters? A: Yes, as long as they are registered with Open Cluster Management and reachable from the hub.

Q: Is there a specific Node.js version required? A: The package runs via npx; use a recent LTS version of Node.js (>=14).

Q: How are credentials managed? A: The server relies on the standard KUBECONFIG environment variable; no additional API keys are needed.

Open Cluster Management MCP Server

The OCM MCP Server provides a robust gateway for Generative AI (GenAI) systems to interact with multiple Kubernetes clusters through the Model Context Protocol (MCP). It facilitates comprehensive operations on Kubernetes resources, streamlined multi-cluster management, and delivered interactive cluster observability.

🚀 Features

🛠️ MCP Tools - Kubernetes Cluster Awareness

✅ Retrieve resources from the hub cluster (current context)
✅ Retrieve resources from the 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 from integrated clusters
❌ Interact with multi-cluster APIs, including Managed Clusters, Policies, Add-ons, and more

📦 Prompt Templates for Open Cluster Management (Planning)

Provide reusable prompt templates tailored for OCM tasks, streamlining agent interaction and automation

📚 MCP Resources for Open Cluster Management (Planning)

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

📌 How to Use

Configure the server using the following snippet:

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

Note: Ensure kubectl is installed. By default, the tool uses the KUBECONFIG environment variable to access the cluster. In a multi-cluster setup, it treats the configured cluster as the hub cluster, accessing others through it.

License

This project is licensed under the MIT License.

Multicluster MCP Server