Multicluster MCP server

The Multi-Cluster MCP Server acts as a gateway, enabling Generative AI (GenAI) systems to interact with multiple Kubernetes clusters using the Model Context Protocol (MCP). It streamlines Kubernetes resource operations, multi-cluster management, and provides interactive cluster observability.

🚀 Features

🛠 Kubernetes Cluster Operations

Supports kubectl for cluster interaction, enabling the creation, updating, and listing of resources like Deployments, Pods, and Services. It can also create, update, and retrieve resources based on CRDs, compressing them to reduce token usage for LLMs.

📊 Cluster Observability

Retrieves and analyzes metrics, logs, and alerts from integrated clusters, providing comprehensive insights.

🌍 Multi-Cluster Management (via Open Cluster Management)

Facilitates access and management of resources across multiple Kubernetes clusters. It allows interaction with multi-cluster APIs, including Managed Clusters, Policies, and Add-ons.

🛠 Installation

Note: Requires kubectl. It uses the KUBECONFIG environment variable for cluster access. In multi-cluster setups, the configured cluster is treated as the hub, accessing others through it. To use with Claude Desktop, add the server configuration to the claude_desktop_config.json file.

License

This project is licensed under the MIT License.