Provides tools for interacting with VMware Aria Operations to perform resource monitoring, alert management, capacity planning, and platform health checks.
VMware Aria Operations MCP Skill
AI-assisted monitoring and capacity planning for VMware Aria Operations (vRealize Operations) via the Model Context Protocol (MCP).
Overview
vmware-aria exposes 18 MCP tools for interacting with Aria Operations through natural language AI agents (Claude Code, Cursor, Goose, etc.):
Category | Tools | Type |
Resources | list, get, metrics, health badge, top consumers | Read-only (5) |
Alerts | list, get, acknowledge, cancel, definitions | Read + 2 Write (5) |
Capacity | overview, remaining, time-remaining, rightsizing | Read-only (4) |
Anomaly | list anomalies, risk badge | Read-only (2) |
Health | platform health, collector groups | Read-only (2) |
Total: 18 tools — 16 read-only, 2 write (acknowledge/cancel alerts)
Quick Start
# Install
uv tool install vmware-aria
# Configure
mkdir -p ~/.vmware-aria
cat > ~/.vmware-aria/config.yaml << 'EOF'
targets:
prod:
host: aria-ops.example.com
username: admin
port: 443
verify_ssl: true
auth_source: LOCAL
default_target: prod
EOF
# Set password (never in config.yaml)
echo "VMWARE_ARIA_PROD_PASSWORD=your_password" > ~/.vmware-aria/.env
chmod 600 ~/.vmware-aria/.env
# Verify setup
vmware-aria doctorCLI Examples
# List top CPU consumers
vmware-aria resource top --metric cpu|usage_average --top 10
# Check active CRITICAL alerts
vmware-aria alert list --criticality CRITICAL
# Acknowledge an alert
vmware-aria alert acknowledge <alert-id>
# Fetch 4-hour CPU + memory metrics for a VM
vmware-aria resource metrics <vm-id> --metrics cpu|usage_average,mem|usage_average --hours 4
# Check cluster capacity
vmware-aria capacity remaining <cluster-id>
vmware-aria capacity time-remaining <cluster-id>
# Find rightsizing opportunities
vmware-aria capacity rightsizing
# Check Aria platform health
vmware-aria health status
vmware-aria health collectorsMCP Setup (Claude Code)
Add to ~/.claude.json:
{
"mcpServers": {
"vmware-aria": {
"command": "vmware-aria-mcp",
"env": {
"VMWARE_ARIA_CONFIG": "~/.vmware-aria/config.yaml"
}
}
}
}Then use natural language:
"Show me the top 10 CPU consumers right now"
"List all CRITICAL alerts and acknowledge them"
"How long until the prod cluster runs out of memory?"
"Which VMs are over-provisioned? Show rightsizing recommendations"
"Are there any anomalies on vm-web-01?"
Authentication
Aria Operations uses OpsToken authentication:
POST /suite-api/api/auth/token/acquire
{"username": "admin", "password": "...", "authSource": "LOCAL"}
→ {"token": "abc123", "validity": 1800000}
Subsequent requests: Authorization: OpsToken abc123Tokens are valid for 30 minutes and automatically refreshed 60 seconds before expiry.
Architecture
User (natural language)
↓
AI Agent (Claude Code / Goose / Cursor)
↓ [reads SKILL.md]
vmware-aria MCP server (stdio transport)
↓ [HTTPS + OpsToken]
Aria Operations Suite API
↓
VMs / Hosts / Clusters / Alerts / CapacityCompanion Skills
Skill | Scope | Tools | Install |
vmware-aiops ⭐ entry point | VM lifecycle, deployment, guest ops, clusters | 31 |
|
Read-only monitoring, alarms, events, VM info | 8 |
| |
NSX networking: segments, gateways, NAT, IPAM | 31 |
| |
DFW microsegmentation, security groups, Traceflow | 20 |
| |
Datastores, iSCSI, vSAN | 11 |
| |
Tanzu Namespaces, TKC cluster lifecycle | 20 |
|
Security
Passwords loaded from env vars or
.envfile, never fromconfig.yamlWrite operations (acknowledge/cancel alert) audit-logged to
~/.vmware-aria/audit.logAPI responses sanitized (control chars stripped, 500-char limit) to prevent prompt injection
Supports self-signed certificates (
verify_ssl: false) for lab environments
License
MIT — see LICENSE