Spark
Sign In
MCP Connector

Manage Kubernetes Across Clusters

Give AI assistants access to Kubernetes resources across a hub and managed clusters via Open Cluster Management (OCM).

Connect
Works with kubernetesnpx
Meng Yan
Own this? Claim it

Maintainer of this project? Claim this page to edit the listing.

86
Spark score
out of 100
Updated Jul 2025
Fresher alternatives ↓
Version 1.0.0
Models
universal
Add to Favorites

Why it matters

Empower generative AI systems to interact with and manage multiple Kubernetes clusters through the Model Context Protocol, simplifying multi-cluster infrastructure management.

Outcomes

What it gets done

01

Retrieve resources from hub and managed clusters.

02

Connect to managed clusters with specified ClusterRoles.

03

Access resources across multiple Kubernetes clusters via Open Cluster Management.

04

Retrieve and analyze metrics, logs, and alerts from integrated clusters.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-multicluster-mcp-sever | bash

Capabilities

Tools your agent gets

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

Overview

Multicluster-MCP-Server MCP Server

Multicluster-MCP-Server lets an AI assistant retrieve Kubernetes resources from a hub cluster and its Open Cluster Management managed clusters, including connecting to a managed cluster via a specified ClusterRole. Use it for AI-assisted resource retrieval in an OCM multi-cluster Kubernetes setup. Metrics/logs/alerts retrieval and broader multi-cluster API interaction are not yet implemented.

What it does

Multicluster-MCP-Server is a gateway that lets Generative AI systems interact with multiple Kubernetes clusters managed via Open Cluster Management (OCM), through the Model Context Protocol. It treats your currently configured cluster as the hub and reaches managed clusters through it.

When to use - and when NOT to

Use it when you run an OCM-based multi-cluster Kubernetes environment and want an AI assistant to retrieve resources from the hub cluster or from managed clusters, including connecting to a managed cluster using a specified ClusterRole. Do not expect metrics/logs/alerts retrieval or deeper multi-cluster API interaction (Managed Clusters, Policies, Add-ons) yet - those are marked as in-progress or not yet implemented in the current version; only hub- and managed-cluster resource retrieval and role-based managed-cluster connection are currently available.

Capabilities

  • Retrieve resources from the hub cluster (the cluster in your current kubectl context).
  • Retrieve resources from managed clusters registered via Open Cluster Management.
  • Connect to a managed cluster using a specified ClusterRole.
  • Access resources across multiple Kubernetes clusters through the OCM hub-and-spoke model.

Planned but not yet available: retrieving and analyzing metrics, logs, and alerts from integrated clusters; and interacting with broader multi-cluster APIs (Managed Clusters, Policies, Add-ons, and more).

How to install

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

Requires kubectl installed. The server uses the KUBECONFIG environment variable by default to access the cluster it treats as the hub; other clusters are accessed through that hub in a multi-cluster setup.

Who it's for

Platform and SRE teams running Open Cluster Management multi-cluster Kubernetes environments who want an AI assistant to retrieve and inspect resources across the hub and managed clusters.

Source README

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

    Mutiple Kubernetes Clusters Operations

    Watch the demo

📦 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.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.