Vmware Privateai
VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 17 tools
- Transport
- Not stated
- Package
- —
- Registry id
- io.github.vmware-skills/vmware-privateai
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
Disclaimer: This is a community-maintained open-source project and is not affiliated with, endorsed by, or sponsored by VMware, Inc., Broadcom Inc., or NVIDIA Corporation. "VMware", "vSphere", and "VCF" are trademarks of Broadcom; "NVIDIA" is a trademark of NVIDIA. Source is auditable at github.com/vmware-skills/VMware-PrivateAI under the MIT license.
Status: pre-MVP skeleton (2026-08-06). Skill #15 of the VMware family. Manages the GPU / AI-infrastructure layer of VMware Private AI Foundation with NVIDIA (PAIF-N) on vSphere 9.x / VCF 9.1 — GPU host/device inventory, vGPU & DirectPath profiles, GPU consumers and utilization, vGPU assignment, and Private AI Service (PAIS) model serving. Independent 1.x version line.
Companion of vmware-aiops (the vCenter VMs behind AI workloads), vmware-vks (GPU-enabled Kubernetes), and vmware-monitor (read-only health). This skill is the GPU lens over all three.
Every API path is verified against official Broadcom/NVIDIA docs before use (see
tests/eval/spec/privateai_endpoints.py) — no endpoints written from memory.
From the project's README.