mirror of
https://github.com/block/goose.git
synced 2026-05-05 15:30:13 +00:00
620133a299
Signed-off-by: Wei Zhou <zw008@github.com> Signed-off-by: Douwe Osinga <douwe@squareup.com> Co-authored-by: Wei Zhou <zw008@github.com> Co-authored-by: Douwe Osinga <douwe@squareup.com>
164 lines
4.9 KiB
Markdown
164 lines
4.9 KiB
Markdown
---
|
|
title: VMware AIops Extension
|
|
description: Add vmware-aiops MCP Server as a goose Extension for natural language VMware vCenter/ESXi operations
|
|
---
|
|
|
|
import Tabs from '@theme/Tabs';
|
|
import TabItem from '@theme/TabItem';
|
|
import CLIExtensionInstructions from '@site/src/components/CLIExtensionInstructions';
|
|
import GooseDesktopInstaller from '@site/src/components/GooseDesktopInstaller';
|
|
|
|
This tutorial covers how to add [vmware-aiops](https://github.com/zw008/VMware-AIops) as a goose extension, enabling natural language management of VMware vCenter and ESXi infrastructure. With this extension, goose can list VMs, check health, power on/off machines, deploy from templates, run commands inside VMs, and orchestrate multi-step operations with automatic rollback.
|
|
|
|
:::tip Quick Install
|
|
<Tabs groupId="interface">
|
|
<TabItem value="ui" label="goose Desktop" default>
|
|
Install vmware-aiops first:
|
|
```sh
|
|
uv tool install vmware-aiops
|
|
vmware-aiops mcp-config install --agent goose
|
|
```
|
|
</TabItem>
|
|
<TabItem value="cli" label="goose CLI">
|
|
```sh
|
|
uv tool install vmware-aiops
|
|
vmware-aiops mcp-config install --agent goose
|
|
```
|
|
</TabItem>
|
|
</Tabs>
|
|
:::
|
|
|
|
## Configuration
|
|
|
|
:::info Prerequisites
|
|
You need [uv](https://docs.astral.sh/uv/) and a running VMware vCenter Server or ESXi host. VMware Tools must be running inside guest VMs for Guest Operations features.
|
|
:::
|
|
|
|
**Step 1: Install and configure credentials**
|
|
|
|
```sh
|
|
uv tool install vmware-aiops
|
|
|
|
mkdir -p ~/.vmware-aiops
|
|
cat > ~/.vmware-aiops/config.yaml << 'EOF'
|
|
targets:
|
|
my-vcenter:
|
|
host: vcenter.example.com
|
|
username: administrator@vsphere.local
|
|
password_env: VMWARE_PASSWORD
|
|
verify_ssl: false
|
|
EOF
|
|
|
|
echo "VMWARE_PASSWORD=your_password" > ~/.vmware-aiops/.env
|
|
chmod 600 ~/.vmware-aiops/.env
|
|
```
|
|
|
|
**Step 2: Verify connectivity**
|
|
|
|
```sh
|
|
vmware-aiops doctor
|
|
```
|
|
|
|
**Step 3: Add to goose**
|
|
|
|
<Tabs groupId="interface">
|
|
<TabItem value="ui" label="goose Desktop" default>
|
|
<GooseDesktopInstaller
|
|
extensionId="vmware-aiops"
|
|
extensionName="VMware AIops"
|
|
description="Natural language VMware vCenter/ESXi monitoring and operations"
|
|
type="stdio"
|
|
command="uvx"
|
|
args={["--from", "vmware-aiops", "vmware-aiops-mcp"]}
|
|
timeout={300}
|
|
envVars={[
|
|
{ name: "VMWARE_AIOPS_CONFIG", label: "Path to config.yaml (e.g. /Users/you/.vmware-aiops/config.yaml)" }
|
|
]}
|
|
/>
|
|
</TabItem>
|
|
<TabItem value="cli" label="goose CLI">
|
|
<CLIExtensionInstructions
|
|
name="vmware-aiops"
|
|
description="Natural language VMware vCenter/ESXi monitoring and operations"
|
|
type="stdio"
|
|
command="uvx --from vmware-aiops vmware-aiops-mcp"
|
|
timeout={300}
|
|
envVars={[
|
|
{ key: "VMWARE_AIOPS_CONFIG", value: "/Users/you/.vmware-aiops/config.yaml" }
|
|
]}
|
|
infoNote={
|
|
<>
|
|
Set <code>VMWARE_AIOPS_CONFIG</code> to the absolute path of your config.yaml. See the <a href="https://github.com/zw008/VMware-AIops" target="_blank" rel="noopener noreferrer">vmware-aiops repository</a> for full setup instructions.
|
|
</>
|
|
}
|
|
/>
|
|
</TabItem>
|
|
</Tabs>
|
|
|
|
## Example Usage
|
|
|
|
In this example, I'll use goose to perform a daily health check across my vCenter environment and remediate a disk space issue on a VM — all via natural language.
|
|
|
|
### goose Prompt
|
|
|
|
```
|
|
Check the health of my vCenter environment. Show any active alarms and
|
|
powered-off VMs that haven't been used recently. If datastore usage is
|
|
above 85%, tell me which VMs are using the most space.
|
|
```
|
|
|
|
### goose Output
|
|
|
|
```
|
|
I'll start with a full health check of your vCenter environment.
|
|
|
|
--- get_alarms ---
|
|
|
|
Found 2 active alarms:
|
|
- esxi-03: CPU ready > 5% (Warning) — sustained for 2 hours
|
|
- datastore02: 87% capacity used (Critical) ← needs attention
|
|
|
|
--- list_virtual_machines (power_state=poweredOff) ---
|
|
|
|
4 powered-off VMs found:
|
|
- vm-test-old (last powered on: 21 days ago)
|
|
- vm-dev-unused (last powered on: 14 days ago)
|
|
- vm-staging-v1 (last powered on: 8 days ago)
|
|
- vm-backup-runner (last powered on: 3 days ago)
|
|
|
|
--- browse_datastore (datastore02) ---
|
|
|
|
Largest consumers on datastore02:
|
|
1. vm-db-prod: 320 GB (snapshots not cleaned up)
|
|
2. vm-web-cluster: 180 GB
|
|
3. vm-test-old: 95 GB (powered off)
|
|
|
|
Recommendation: Delete vm-test-old (powered off 21 days, 95 GB) to free
|
|
space immediately. Also, vm-db-prod has stale snapshots — consolidating
|
|
them would recover ~120 GB.
|
|
|
|
Shall I create a plan to remove vm-test-old and consolidate vm-db-prod snapshots?
|
|
```
|
|
|
|
```
|
|
Yes, go ahead.
|
|
```
|
|
|
|
```
|
|
--- vm_create_plan ---
|
|
|
|
Plan created:
|
|
Step 1: Power off check for vm-test-old (already off ✓)
|
|
Step 2: Delete vm-test-old
|
|
Step 3: Consolidate snapshots on vm-db-prod
|
|
|
|
⚠️ Step 2 is irreversible. Step 3 is safe (read-only snapshot merge).
|
|
|
|
--- vm_apply_plan ---
|
|
|
|
Step 1/3: Verified vm-test-old is powered off ✓
|
|
Step 2/3: Deleted vm-test-old — freed 95 GB ✓
|
|
Step 3/3: Consolidated vm-db-prod snapshots — freed 118 GB ✓
|
|
|
|
datastore02 is now at 64% capacity. All alarms should clear within 5 minutes.
|
|
```
|