Rhoai Observability MCP
未认领MCP server for troubleshooting vLLM inference workloads on Red Hat OpenShift AI — queries Prometheus, Alertmanager, Loki, Grafana, and Kubernetes from AI assistants.
安装
uv pip install -e ".[dev]"更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
21 个工具中显示 21 个
文档中列出的工具 (21)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
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