A Model Context Protocol server
npm install @mseep/multicluster-mcp-serverThe Multi-Cluster 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.
ā
Fully supports kubectl to interact with your cluster
ā Create, update, and list resources (Deployments, Pods, Services, etc.)
ā Create, update, and retrieve resources based on the CRD (the tool retrieves and compresses the CRD, preserving all information while reducing tokens for the LLM).
Kubernetes Operations
ā Retrieve and analyze metrics, logs, and alerts from integrated clusters
ā Access and manage resources across multiple Kubernetes clusters
Mutiple Kubernetes Operations

ā Interact with multi-cluster APIs, including Managed Clusters, Policies, Add-ons, and more
š 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.
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
``json``
{
"mcpServers": {
"y": {
"command": "/path/to/multicluster-mcp-server/build/index.js"
}
}
}
This project is licensed under the MIT License.