Horizon MCP Server

create_desktop_pool

Creates a new desktop pool in Horizon, provisioning VMs for automated pools. Confirm with user before use, as provisioning starts immediately.

Instructions

Create a new desktop pool.

CAUTION: Provisioning an AUTOMATED pool immediately begins creating VMs in vCenter. Always confirm with the user before calling this.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`spec`	Yes	Full pool specification, verified against a live Horizon server (2606). Required top-level keys: name, type (AUTOMATED \| MANUAL \| RDS), source (INSTANT_CLONE \| LINKED_CLONE \| VIRTUAL_CENTER \| RDS \| UNMANAGED), user_assignment (FLOATING \| DEDICATED), naming_method (SPECIFIED \| PATTERN), access_group_id (required for AUTOMATED/MANUAL pools — get one from the horizon://config/local-access-groups resource). AUTOMATED pools ALSO require these — all top-level, NOT nested under provisioning_settings, despite what that name suggests: vcenter_id (from list_virtual_centers); provisioning_settings: {parent_vm_id (list_base_vms), base_snapshot_id (list_base_vm_snapshots), datacenter_id (list_datacenters), vm_folder_id (list_vm_folders), host_or_cluster_id (list_hosts_or_clusters), resource_pool_id (list_resource_pools)}; storage_settings: {datastores: [{datastore_id}]} (list_datastores); customization_settings: {customization_type: 'CLONE_PREP' for instant clone, ad_container_rdn (list_ad_domains + list_ad_containers), instant_clone_domain_account_id (list_ic_domain_accounts)}; pattern_naming_settings: {naming_pattern, max_number_of_machines} when naming_method='PATTERN'. nics is optional and top-level (network_interface_card_id + network_label_assignment_specs) — if omitted, new machines simply inherit the parent image's existing network settings.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.2.0Sep 30, 2026

changedInput schema / properties / spec / description

Previous value: -"Full pool specification. Required keys: name, type (AUTOMATED | MANUAL), source (INSTANT_CLONE | VIRTUAL_CENTER | RDS), user_assignment (FLOATING | DEDICATED). AUTOMATED pools also require provisioning_settings with: virtual_center_id, parent_vm_id, snapshot_id, datacenter_id, vm_folder_id, host_or_cluster_id, resource_pool_id, datastores ([{datastore_id}]), nics ([{nic_id, network_label_id}]), naming_pattern, max_machine_count. Use list_virtual_centers, list_base_vms, list_base_vm_snapshots, list_datacenters, list_vm_folders, list_hosts_or_clusters, list_datastores, list_resource_pools, and list_network_labels to look up all required IDs."New value: +"Full pool specification, verified against a live Horizon server (2606). Required top-level keys: name, type (AUTOMATED | MANUAL | RDS), source (INSTANT_CLONE | LINKED_CLONE | VIRTUAL_CENTER | RDS | UNMANAGED), user_assignment (FLOATING | DEDICATED), naming_method (SPECIFIED | PATTERN), access_group_id (required for AUTOMATED/MANUAL pools — get one from the horizon://config/local-access-groups resource). AUTOMATED pools ALSO require these — all top-level, NOT nested under provisioning_settings, despite what that name suggests: vcenter_id (from list_virtual_centers); provisioning_settings: {parent_vm_id (list_base_vms), base_snapshot_id (list_base_vm_snapshots), datacenter_id (list_datacenters), vm_folder_id (list_vm_folders), host_or_cluster_id (list_hosts_or_clusters), resource_pool_id (list_resource_pools)}; storage_settings: {datastores: [{datastore_id}]} (list_datastores); customization_settings: {customization_type: 'CLONE_PREP' for instant clone, ad_container_rdn (list_ad_domains + list_ad_containers), instant_clone_domain_account_id (list_ic_domain_accounts)}; pattern_naming_settings: {naming_pattern, max_number_of_machines} when naming_method='PATTERN'. nics is optional and top-level (network_interface_card_id + network_label_assignment_specs) — if omitted, new machines simply inherit the parent image's existing network settings."

First observedv0.1.0Sep 10, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a non-read-only, non-idempotent, non-destructive mutation, but the description adds genuinely valuable behavioral context beyond them: an AUTOMATED pool immediately begins creating VMs in vCenter and requires user confirmation. It stops short of covering auth/permission needs or the fact that each call produces a distinct new pool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and followed by the critical caution. Every sentence earns its place with zero redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, and the schema fully specifies the complex 'spec' object. The description covers the key provisioning risk, though it omits auth/permission prerequisites and any mention of idempotency behavior that would round it out.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the 'spec' object is exhaustively documented inline (required keys, nested settings, cross-referenced sibling tools for IDs). The description adds no parameter meaning of its own, so the baseline of 3 for high-coverage schemas applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Create) and resource (desktop pool), clearly distinct from sibling creation tools like create_rdsh_farm and create_application_pool. An agent immediately knows this tool's job.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Always confirm with the user before calling this' directive is a useful usage guardrail, but it does not tell the agent when to choose this tool over alternatives (e.g. create_rdsh_farm for RDSH workloads) or what prerequisites must be gathered first. Usage is implied rather than fully specified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server