OpenShift SRE Copilot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HCP_TOKEN | No | Bearer token for ROSA HCP cluster | |
| ARO_API_URL | No | API URL of the ARO cluster | |
| HCP_API_URL | No | API URL of the ROSA HCP cluster | |
| ARO_PASSWORD | No | Password for ARO cluster | |
| ARO_USERNAME | No | Username for ARO cluster | |
| HCP_PASSWORD | No | Password for ROSA HCP cluster | |
| HCP_USERNAME | No | Username for ROSA HCP cluster | |
| ARO_CLUSTER_NAME | No | Name of the ARO cluster | |
| HCP_CLUSTER_NAME | No | Name of the ROSA HCP cluster |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_clustersA | List all available OpenShift clusters |
| get_cluster_healthA | Get overall health status of an OpenShift cluster including nodes, operators, and critical workloads |
| get_nodesB | List all nodes in the cluster with status and resource information |
| get_podsB | List pods in a namespace with their status |
| get_failing_podsA | Get pods that are not in Running state (CrashLoopBackOff, Error, Pending, etc.) |
| get_eventsB | Get recent Kubernetes events for troubleshooting |
| diagnose_crashloopB | Diagnose a pod in CrashLoopBackOff state and provide remediation suggestions |
| get_storage_infoC | Get storage information including PVCs and their status |
| get_cluster_operatorsC | Get status of OpenShift cluster operators |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Tools have distinct purposes, with slight overlap between get_pods and get_failing_pods, but descriptions clearly differentiate them. Others like diagnose_crashloop and get_cluster_health are distinct.
All tools follow a consistent verb_noun pattern (diagnose_, get_, list_), with clear and predictable naming.
With 9 tools, the set is well-scoped for an SRE diagnosis and monitoring tool, covering essential operations without bloat.
Covers key diagnosis tasks (health, pods, nodes, events, storage, crash loops). Missing log retrieval or resource updates, but fits a focused diagnostic scope.