Rhoai Observability MCP
UnclaimedMCP server for troubleshooting vLLM inference workloads on Red Hat OpenShift AI — queries Prometheus, Alertmanager, Loki, Grafana, and Kubernetes from AI assistants.
Install
uv pip install -e ".[dev]"Set up this server
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
21 of 21 tools
Documented tools (21)
From project documentation. A server handshake does not verify each tool’s description or behavior.
describe_resource
Get detailed description of a Kubernetes resource
get_alert_groups
Get alerts grouped by their routing labels
get_alerts
Get active alerts from Alertmanager, filterable by severity and labels
get_dashboard_panels
Get panels and their queries from a Grafana dashboard
get_events
List Kubernetes events, filterable by resource and reason
get_inference_services
List KServe InferenceService resources
get_node_status
Get node status, capacity, and GPU allocation info
get_pod_logs
Get logs for a specific pod by namespace and name
get_pods
List pods in a namespace with status, restarts, and creation time
get_trace
Fetch a distributed trace by its trace ID
get_vllm_metrics
Get a summary of key vLLM metrics (TTFT, TPOT, E2E, cache, queue) for a model
investigate_errors
Correlate error logs, alerts, and Kubernetes events in a namespace
investigate_gpu
Correlate GPU utilization, KV cache, queue depth, and pod status
investigate_latency
Correlate latency metrics, error logs, and alerts for a vLLM model
list_dashboards
List available Grafana dashboards, filterable by tag or title
list_metrics
List available Prometheus metric names, optionally filtered by regex
list_trace_tags
List available trace tag names for building TraceQL queries
query_logs
Execute a LogQL query against OpenShift LokiStack
query_prometheus
Execute a raw PromQL query against ThanosQuerier
query_prometheus_range
Execute a PromQL range query to get time-series data (trends, spikes, correlations)
search_traces
Search for traces using TraceQL expressions
Tool change history
FAQ
Questions about Rhoai Observability MCP Server
- How do I connect Rhoai Observability MCP Server to Claude?
- The listing records `uv pip install -e ".[dev]"` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop as compatible clients.
- Is Rhoai Observability MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Rhoai Observability MCP Server do?
- Rhoai Observability MCP Server documents 21 tools to the agent, including describe_resource, get_alert_groups, get_alerts. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.