Loading…
AI-powered multicluster management: Querying fleet health with OpenShift Lightspeed and Red Hat Advanced Cluster Management
Diego Alvarez Ponce, Luiz Bernardo Levenhagen
- Source
- Red Hat
- Published
- Added to Yomu
Summary
Managing modern large-scale Kubernetes fleets across distributed clusters can make troubleshooting slow because administrators must build manual search queries and sift scattered outputs. The post presents a Technology Preview MCP server for Red Hat Advanced Cluster Management that translates natural-language prompts into structured searches across managed clusters, deployed with Helm in the hub cluster. OpenShift Lightspeed is configured through its OLSConfig custom resource to call the MCP endpoint, use a Kubernetes service-account token for internal authorization, and optionally skip approval for read-only searches. The examples cover finding clusters below OpenShift 4.21, locating pods in a specified cluster and namespace, and identifying an unhealthy VM across the fleet; one result finds dev-vm in an ErrorUnschedulable condition and provides diagnostic guidance.
Context
Managing large-scale Kubernetes environments across distributed clusters increases cognitive load and can slow visibility and troubleshooting. Administrators using Red Hat Advanced Cluster Management traditionally construct manual search queries and sift through scattered cluster outputs to answer fleet-wide questions.
Approach / What changed
Deploy the Red Hat Advanced Cluster Management MCP server in the hub cluster with Helm, then register its service endpoint in the OpenShift Lightspeed OLSConfig custom resource. The configuration uses a Kubernetes service-account token for internal authorization and can bypass approval gates because the MCP server performs read-only searches.
Takeaways
- The MCP server translates natural-language prompts into Red Hat Advanced Cluster Management Search expressions and executes them against the hub cluster.
- OpenShift Lightspeed can use the MCP server to retrieve resources from a specified managed cluster and namespace, such as pods in production and app-prod.
- A fleet-wide query identified dev-vm in the development managed cluster as stuck in an ErrorUnschedulable condition and returned diagnostic guidance.