nutanix-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NUTANIX_ALLOW_POWER | No | Set to 'true' to enable power-on and power-off VM tools. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_vmsA | List all VMs visible to the Prism Central deployment. Returns names, ext IDs, power state, host, cluster, memory and CPU config. Use this when an agent needs to discover what VMs exist in the Nutanix environment, check VM inventory, or find a specific VM by name to inspect further. |
| get_vmA | Get full metadata for a single VM by its ext_id. Returns complete VM configuration including power state, resources, network adapters, disk configuration, and cluster assignment. Use this when you have a specific VM ext_id and need detailed information about that VM. |
| power_on_vmA | Transition a VM from Off to On. This is an environment-gated operation that requires NUTANIX_ALLOW_POWER=true. Use this when an agent needs to start a stopped VM, such as bringing a VM online for maintenance, testing, or restoring service. Returns an error if the environment variable is not set. |
| power_off_vmA | Transition a VM from On to Off (graceful shutdown). This is an environment-gated operation that requires NUTANIX_ALLOW_POWER=true. Use this when an agent needs to stop a running VM, such as for maintenance, resource consolidation, or decommissioning. Returns an error if the environment variable is not set. |
| list_clustersA | Inventory all clusters under Prism Central. Returns cluster names, ext IDs, health status, version, and resource summary. Use this when an agent needs to understand the cluster topology, check cluster health across the fleet, or find a specific cluster for VM placement. |
| get_clusterA | Read full configuration and health of a single cluster. Returns complete cluster details including nodes, storage, networking, and health metrics. Use this when you have a specific cluster ext_id and need detailed information about that cluster's configuration and current state. |
| list_alertsA | Stream the current alert backlog from Prism Central. Returns all active alerts with severity, category, affected entity, and timestamp. Use this when an on-call agent needs to triage what is unhealthy across the fleet, prioritize incident response, or check for infrastructure issues affecting VMs or clusters. |
| list_subnetsA | Inventory all networking subnets visible to Prism Central. Returns subnet names, ext IDs, VLAN IDs, network address ranges, and cluster assignment. Use this when an agent is placing a new VM and needs to pick the right network, or when checking available network segments for VM connectivity. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct resource and action: cluster vs VM vs alert vs subnet, with clear read/list vs power control boundaries. No two tools could be confused for the same purpose.
All tool names follow a consistent verb_noun pattern with underscores (e.g., list_vms, power_on_vm). No mixing of styles or vague verbs.
8 tools cover the core operations for Nutanix infrastructure: inventory (list), detail retrieval (get), alert monitoring, and power management. The scope is well-defined without being excessive or too sparse.
While the tool set covers essential read operations and power control, it lacks create, update, or delete for VMs and clusters, which are common tasks. The surface is incomplete for full lifecycle management.