NVIDIA/AI-Factory-Operations-Agent

observability

Analyze cluster observability data and create Grafana dashboards. Use when the user asks about metrics, logs, log labels, cluster health history, dashboards, charts, panels, or visualizations.

ai-factory-operations-agent-headless

Use AI Factory Operations Agent without opening the browser UI. Invoke it through the headless HTTP API, packaged CLI, or stdio MCP server, and deploy it first when no service is available.

grafana

Create and open Grafana dashboards for metrics, Loki logs, and mixed panels. Use when the user asks for a dashboard, visualization, chart, panel, or graph of GPU, Base Command Manager (BCM), node, network, InfiniBand, Prometheus metrics, or Loki logs.

gpu-networking

Measure and diagnose distributed GPU networking performance: NCCL collectives, RDMA transport, PCIe topology, link health, IOMMU and ACS. Use for current bandwidth/latency questions and follow-up bottleneck investigations or corrections.

bcm

Inspect Base Command Manager (BCM) inventory and health evidence, and make explicitly requested changes when Base Command Manager edit mode is enabled.

iraop

Research NVIDIA DGX, SuperPOD, GB200, NVLink, BlueField, Base Command Manager (BCM), and on-prem infrastructure documentation through the IRA/Sequoia retrieval agent. Use when the user asks to research docs, deployment policy, operational guidance, or newly…

hardware-agent

Triage hardware faults on NVIDIA GPU compute nodes through the Hardware Agent. Starting a triage is read-only log collection and hardware_analyze_dut is available in View mode; never require Edit or Auto. Before asking to start any fresh NVDebug collection,…

slurm

Inspect mounted Slurm accounting exports and job logs for failed workload root cause analysis.