vmware-aiops

What this skill does

# VMware AIops

AI-powered VMware vCenter and ESXi operations tool. Manage your entire VMware infrastructure using natural language through any AI coding assistant.

> **Need read-only monitoring only?** Use [VMware-Monitor](https://github.com/zw008/VMware-Monitor) — an independent repository with code-level safety (zero destructive code in the codebase). Install: `clawhub install vmware-monitor`

## When to Use This Skill

- Query VM, host, datastore, cluster, and network inventory
- Check health status, active alarms, hardware sensors, and event logs
- Perform VM lifecycle operations: power on/off, create, delete, snapshot, clone, migrate
- Deploy VMs from OVA, templates, linked clones, or batch specs
- Create and manage clusters: HA/DRS configuration, add/remove hosts
- Configure iSCSI storage: enable adapter, add/remove targets, rescan
- Browse datastores and discover ISO/OVA/VMDK images
- Monitor vSAN health, capacity, disk groups, and performance
- Access Aria Operations (VCF Operations) for historical metrics, anomaly detection, and capacity planning
- Manage vSphere Kubernetes Service (VKS) clusters
- Run scheduled scanning with webhook notifications (Slack, Discord)

## Quick Install

All install methods fetch from the same source: [github.com/zw008/VMware-AIops](https://github.com/zw008/VMware-AIops) (MIT licensed). We recommend reviewing the source code before installing.

```bash
# Via Skills.sh (fetches from GitHub)
npx skills add zw008/VMware-AIops

# Via ClawHub (fetches from ClawHub registry snapshot of GitHub)
clawhub install vmware-aiops

# Via PyPI (recommended for version pinning)
uv tool install vmware-aiops==1.0.16
```

### Claude Code

```
/plugin marketplace add zw008/VMware-AIops
/plugin install vmware-ops
/vmware-ops:vmware-aiops
```

## Usage Mode

Choose the best mode based on your environment:

| Scenario | Recommended Mode | Why |
|----------|-----------------|-----|
| **Cloud models** (Claude, GPT-4o, Gemini) | MCP or CLI | Both work well; MCP gives structured JSON I/O |
| **Local/small models** (Ollama, Llama, Qwen <32B) | **CLI** | Lower token cost (~2K vs ~10K), higher accuracy — small models struggle with 31 MCP tool schemas |
| **Token-sensitive workflows** | **CLI** | CLI via SKILL.md uses ~2K tokens; MCP loads ~10K tokens of tool definitions into every conversation |
| **Automated pipelines / Agent chaining** | **MCP** | Structured JSON input/output, type-safe parameters, no shell parsing |

### Calling Priority

- **MCP-native tools** (Claude Code, Cursor): MCP first, CLI fallback
- **Local models / Token-sensitive**: CLI first (MCP not needed)
- **All other tools**: CLI first

> **Tip**: For token-sensitive scenarios, use CLI mode — the AI reads SKILL.md (~2K tokens) and calls commands via Bash. MCP mode loads all 31 tool schemas (~10K tokens) into context on every conversation turn.

### CLI Examples

```bash
# Activate venv first
source /path/to/VMware-AIops/.venv/bin/activate

# Inventory
vmware-aiops inventory vms --target home-esxi
vmware-aiops inventory hosts --target home-esxi

# Health
vmware-aiops health alarms --target home-esxi

# VM operations
vmware-aiops vm info my-vm --target home-esxi
vmware-aiops vm power-on my-vm --target home-esxi
```

### MCP Mode (Optional)

For Claude Code / Cursor users who prefer structured tool calls, add to `~/.claude/settings.json`:

```json
{
  "mcpServers": {
    "vmware-aiops": {
      "command": "/path/to/VMware-AIops/.venv/bin/python",
      "args": ["-m", "mcp_server"],
      "cwd": "/path/to/VMware-AIops",
      "env": {
        "VMWARE_AIOPS_CONFIG": "~/.vmware-aiops/config.yaml"
      }
    }
  }
}
```

MCP exposes 43 tools across 8 categories. All accept optional `target` parameter.

| Category | Tools |
|----------|-------|
| Inventory | `list_virtual_machines`, `list_esxi_hosts`, `list_all_datastores`, `list_all_clusters` |
| Health | `get_alarms`, `get_events`, `vm_info` |
| VM Lifecycle | `vm_power_on`, `vm_power_off`, `vm_set_ttl`, `vm_cancel_ttl`, `vm_list_ttl`, `vm_clean_slate` |
| Deployment | `deploy_vm_from_ova`, `deploy_vm_from_template`, `deploy_linked_clone`, `attach_iso_to_vm`, `convert_vm_to_template`, `batch_clone_vms`, `batch_linked_clone_vms`, `batch_deploy_from_spec` |
| Guest Operations | `vm_guest_exec`, `vm_guest_upload`, `vm_guest_download` |
| Plan → Apply | `vm_create_plan`, `vm_apply_plan`, `vm_rollback_plan`, `vm_list_plans` |
| Datastore | `browse_datastore`, `scan_datastore_images`, `list_cached_images` |
| Cluster | `cluster_create`, `cluster_delete`, `cluster_add_host`, `cluster_remove_host`, `cluster_configure`, `cluster_info` |
| Storage / iSCSI | `storage_iscsi_enable`, `storage_iscsi_status`, `storage_iscsi_add_target`, `storage_iscsi_remove_target`, `storage_rescan` |

`list_virtual_machines` auto-compacts when inventory exceeds 50 VMs (returns compact fields only). Use `limit` or `fields` to override.

## Architecture

```
User (Natural Language)
  ↓
AI Tool (Claude Code / Aider / Gemini / Codex / Cursor / Trae / Kimi)
  ↓
  ├─ CLI mode (default): vmware-aiops CLI ──→ pyVmomi ──→ vSphere API
  │
  └─ MCP mode (optional): MCP Server (stdio) ──→ pyVmomi ──→ vSphere API
  ↓
vCenter Server ──→ ESXi Clusters ──→ VMs
    or
ESXi Standalone ──→ VMs
```

## Capabilities

### 1. Inventory

| Feature | vCenter | ESXi | Details |
|---------|:-------:|:----:|---------|
| List VMs | ✅ | ✅ | Name, power state, CPU, memory, guest OS, IP |
| List Hosts | ✅ | ⚠️ Self only | CPU cores, memory, ESXi version, VM count, uptime |
| List Datastores | ✅ | ✅ | Capacity, free/used, type (VMFS/NFS), usage % |
| List Clusters | ✅ | ❌ | Host count, DRS/HA status |
| List Networks | ✅ | ✅ | Network name, associated VM count |

### 2. Health & Monitoring

| Feature | vCenter | ESXi | Details |
|---------|:-------:|:----:|---------|
| Active Alarms | ✅ | ✅ | Severity, alarm name, entity, timestamp |
| Event/Log Query | ✅ | ✅ | Filter by time range, severity; 50+ event types |
| Hardware Sensors | ✅ | ✅ | Temperature, voltage, fan status |
| Host Services | ✅ | ✅ | hostd, vpxa running/stopped status |

**Monitored Event Types:**

| Category | Events |
|----------|--------|
| VM Failures | `VmFailedToPowerOnEvent`, `VmDiskFailedEvent`, `VmFailoverFailed` |
| Host Issues | `HostConnectionLostEvent`, `HostShutdownEvent`, `HostIpChangedEvent` |
| Storage | `DatastoreCapacityIncreasedEvent`, SCSI high latency |
| HA/DRS | `DasHostFailedEvent`, `DrsVmMigratedEvent`, `DrsSoftRuleViolationEvent` |
| Auth | `UserLoginSessionEvent`, `BadUsernameSessionEvent` |

### 3. VM Lifecycle

| Operation | Command | Confirmation | vCenter | ESXi |
|-----------|---------|:------------:|:-------:|:----:|
| Power On | `vm power-on <name>` | — | ✅ | ✅ |
| Graceful Shutdown | `vm power-off <name>` | Double | ✅ | ✅ |
| Force Power Off | `vm power-off <name> --force` | Double | ✅ | ✅ |
| Reset | `vm reset <name>` | — | ✅ | ✅ |
| Suspend | `vm suspend <name>` | — | ✅ | ✅ |
| VM Info | `vm info <name>` | — | ✅ | ✅ |
| Create VM | `vm create <name> --cpu --memory --disk` | — | ✅ | ✅ |
| Delete VM | `vm delete <name>` | Double | ✅ | ✅ |
| Reconfigure | `vm reconfigure <name> --cpu --memory` | Double | ✅ | ✅ |
| Create Snapshot | `vm snapshot-create <name> --name <snap>` | — | ✅ | ✅ |
| List Snapshots | `vm snapshot-list <name>` | — | ✅ | ✅ |
| Revert Snapshot | `vm snapshot-revert <name> --name <snap>` | — | ✅ | ✅ |
| Delete Snapshot | `vm snapshot-delete <name> --name <snap>` | — | ✅ | ✅ |
| Clone VM | `vm clone <name> --new-name <new>` | — | ✅ | ✅ |
| vMotion | `vm migrate <name> --to-host <host>` | — | ✅ | ❌ |
| Set TTL | `vm set-ttl <name> --minutes <n>` | — | ✅ | ✅ |
| Cancel TTL | `vm cancel-ttl <name>` | — | ✅ | ✅ |
| List TTLs | `vm list-ttl` | — | ✅ | ✅ |
| Clean Slate | `vm clean-slate <name> [--snapshot baseline]` | Double | ✅ | ✅ |
| Guest Exec | `vm guest-exec <name> --cmd /bin/bash --args "-c 'whoami'"` | — | ✅ | ✅ |
| Guest Upload | `vm guest-upload <name> --local f.s