Developer-tools MCP server

VMware AIops

Version history of discovered tools, schemas, and declared agent authority.

View watchlist

DistributionDistribution: PyPI
Packagevmware-aiops
Latest analyzed version2.5.2
Current tool count61
Latest analysisNov 17, 2026
Package source

OBSERVED INTERFACE

Capability surface

Modelara’s observed declarations are shown separately from its derived effect classifications.

3 releases analyzed2.5.0 → 2.5.2Latest: 2.5.2
  • read18
  • write26
  • destructive17
  • unknown0

Unknown means Valyd could not determine the capability's effect confidently from the declared interface and static evidence. It is not treated as safe.

Package
vmware-aiops@2.5.2
Registry
pypi
Published
Nov 16, 2026
Integrity
sha256-koLTAD2k7vkXkb+9ZOfre/BVzH9xhk8uOlp8kq2ZDg0=
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/vmware-skills/VMware-AIops

61 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
acknowledge_vcenter_alarmvmware-skills-vmware-aiops:tool:acknowledge_vcenter_alarm
Observed interface and hashes

[WRITE] Acknowledge a triggered vCenter alarm — marks it as seen WITHOUT clearing it. This only marks the alarm; it does not clear it. The alarm stays in the active list with acknowledged=true until its condition clears or it is reset. To remove it entirely after fixing the root cause use reset_vcenter_alarm instead. Get exact entity_name and alarm_name from list_vcenter_alarms first; an unknown pair returns a not-found error. Returns: Dict: entity_name, alarm_name, action ("acknowledged"), acknowledged (true).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "alarm_name": {
      "description": "Exact alarm definition name, e.g. \"Virtual machine CPU usage\".",
      "title": "Alarm Name",
      "type": "string"
    },
    "entity_name": {
      "description": "VM, ESXi host, or cluster the alarm fired on (from list_vcenter_alarms output).",
      "title": "Entity Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "entity_name",
    "alarm_name"
  ],
  "title": "acknowledge_vcenter_alarmArguments",
  "type": "object"
}
sha256:f44c387229565676a546f98e590ed70b534ee23e20ad65b2b73756c02306cd8c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:39a45863d2038ad7ba45c81b6050cea4d3cd7b090fe3f03e82ba0d5d9c12ce48

Interface hash: sha256:69db88505ead36b3c8045bd37d86ebded15dfc15b4578837f67e9525aa484092

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/acknowledge_vcenter_alarm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "acknowledge_vcenter_alarm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:1dd98f1023b37dcf8ddc3e09a2e44fb1d658257dd2cda2be517376a01ef8fcea"
}
toolwrite2.5.0No change observed
add_cluster_hostvmware-skills-vmware-aiops:tool:add_cluster_host
Observed interface and hashes

[WRITE] Move an ESXi host that vCenter already manages into a cluster. The host must already be in vCenter inventory (standalone or in another cluster) — this does NOT register brand-new hosts and takes no host credentials; use the vCenter UI for first-time registration. Idempotent: a host already in the cluster returns success without change. Maintenance mode is not required to join (it IS required by remove_cluster_host). Check membership first with get_cluster_info. Returns a status string: moved, already-in-cluster, or a not-found error.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster_name": {
      "description": "Destination cluster (create with create_cluster).",
      "title": "Cluster Name",
      "type": "string"
    },
    "host_name": {
      "description": "Host name as shown in vCenter inventory, usually the FQDN, e.g. \"esxi-01.lab.local\".",
      "title": "Host Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target from config.yaml; omit for the default target.",
      "title": "Target"
    }
  },
  "required": [
    "cluster_name",
    "host_name"
  ],
  "title": "add_cluster_hostArguments",
  "type": "object"
}
sha256:b6a93fec1594484816a4ad742450a402df34511d4ba7cfdec9784deeec56c2e4

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "add_cluster_hostOutput",
  "type": "object"
}
sha256:91c892df371b3c6b23c2e6415539fb7cb2c9a0c767a95449509982608137f6ae

Description hash: sha256:36fe3ced0dd801752a1de7289a6b1c38745753740e920ef7712c82119676fad9

Interface hash: sha256:6fe89e6e982048eff918d79725ae0d8d6af003987715ddf8d16f97ec792a1a88

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/add_cluster_host",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "add_cluster_host"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2bf0f62eb5e0b0d3a02cf4dd5d5716f84e274e5650740c6a5fa8d594af2e83db"
}
toolwrite2.5.0No change observed
add_host_vmkvmware-skills-vmware-aiops:tool:add_host_vmk
Observed interface and hashes

[WRITE] Add a static-IP VMkernel adapter on a DVS portgroup - preview/confirm gated. Deliberately minimal shape for throwaway test vmks on L2-only segments (e.g. a TEP VLAN): static IPv4, NO gateway, NO services enabled. The DVS port allocation is handled internally - pass the distributed portgroup name. confirm=False validates (host + portgroup exist, IP/netmask/MTU legal, IP not already on the host) and returns the exact spec without writing; confirm=True creates and returns the assigned device name. Verify with list_host_vmks; remove with remove_host_vmk. Audited. Returns: Preview dict (action="preview") or result dict (action="created", device=e.g. "vmk2"). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True creates it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "host_name": {
      "description": "ESXi host to add the vmk on.",
      "title": "Host Name",
      "type": "string"
    },
    "ip": {
      "description": "Static IPv4 address for the vmk.",
      "title": "Ip",
      "type": "string"
    },
    "mtu": {
      "default": 1500,
      "description": "MTU for the vmk (default 1500; 9000 for jumbo tests).",
      "title": "Mtu",
      "type": "integer"
    },
    "netmask": {
      "description": "Subnet mask (e.g. 255.255.255.0).",
      "title": "Netmask",
      "type": "string"
    },
    "portgroup": {
      "description": "Distributed portgroup name to connect to.",
      "title": "Portgroup",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "host_name",
    "portgroup",
    "ip",
    "netmask"
  ],
  "title": "add_host_vmkArguments",
  "type": "object"
}
sha256:b628417489e709ebf3e0e8f49071ca51ecb67d5df410b77f94bd1176b19305a4

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:f178f2fccf4299b67cbba109d043ecb498c1fdaa58cad1af5b3ee0facdde5634

Interface hash: sha256:2bac7bb7ab57efa4684274b41ad092b752f033fd73d0795423cbf2874f972143

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/add_host_vmk",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "add_host_vmk"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:15c8fc6be65a8ccca91422d01eb9c8bdacab85fc1a7c8c2bbc00760930bcbf55"
}
toolwrite2.5.0No change observed
apply_vm_planvmware-skills-vmware-aiops:tool:apply_vm_plan
Observed interface and hashes

[WRITE] Execute a previously created plan step by step. Without confirm=True this only previews: it returns blast_radius listing every step (index, action, target object), the count and indices of the destructive ones (delete, power off, revert, guest commands...), and blockers — and runs nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Each step is shown with its full parameters (passwords redacted). Each destructive step is measured as its own tool would measure it (delete_vm, power_off_vm, revert_vm_snapshot, run_vm_guest_command, delete_cluster ...), and that tool's blockers refuse the plan. A step on something an earlier step creates or changes is marked check "deferred": it is measured immediately before it runs, and the plan stops there if it fails. Refused: a step that ~/.vmware/rules.yaml denies for the tool that does the same thing (a plan step delete_vm is authorized as delete_vm, power_off as power_off_vm, and so on, also just before it runs), a target other than the one the plan was created against (no target is a target of its own), a step its tool would refuse, anything it could not read, a delete_vm step without its acknowledge_blast_radius (from a delete_vm preview), and any iscsi_* or storage_rescan step — those are gated in vmware-storage; run enable_iscsi, add_iscsi_target, remove_iscsi_target or rescan_storage there. With confirm=True steps run sequentially. On failure: stops immediately, keeps the plan file with per-step results, and returns rollback_available. On success: deletes the plan file. If a step fails and rollback_available is true, ask the user whether to rollback, then call rollback_vm_plan.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "plan_id": {
      "description": "The plan ID returned by create_vm_plan.",
      "title": "Plan Id",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The vCenter/ESXi target the plan was created against.",
      "title": "Target"
    }
  },
  "required": [
    "plan_id"
  ],
  "title": "apply_vm_planArguments",
  "type": "object"
}
sha256:96009f3be6d6b49997138fca6a0c6934af79a156648255154acb935926ee3b65

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:d3aba06664b3df148268766faf5accfecd5033baabf792322d375af4d1dab052

Interface hash: sha256:5509cf8c8a02ca1a5e9e936e19cbb0e5d42a53c897ac04a0d2518110fa9d8a9d

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/apply_vm_plan",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "apply_vm_plan"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2d4defa7c72ae6ce28925241c944d014e3780e8a45f17a014a7c800eab63dc13"
}
tooldestructive2.5.0No change observed
attach_iso_to_vmvmware-skills-vmware-aiops:tool:attach_iso_to_vm
Observed interface and hashes

[WRITE] Mount a datastore ISO into a VM's virtual CD-ROM drive. Reconfigures the existing CD-ROM (replacing any mounted ISO) or adds one on the VM's IDE controller; fails with a clear message if the VM has no IDE controller. Works whether the VM is powered on or off. Find ISO paths first with browse_datastore using pattern "*.iso". Returns a status string confirming attachment, or a VM-not-found / no-IDE-controller error.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "iso_ds_path": {
      "description": "Datastore path in bracket format, e.g. \"[datastore1] iso/ubuntu-22.04.iso\".",
      "title": "Iso Ds Path",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target from config.yaml; omit for the default target.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact VM name as shown in vCenter inventory.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "iso_ds_path"
  ],
  "title": "attach_iso_to_vmArguments",
  "type": "object"
}
sha256:d40364ebe5835a6ac841d4ae20ac617e12734a0370331fb5105b12fd96a4f1d8

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "attach_iso_to_vmOutput",
  "type": "object"
}
sha256:867d8dbef7ea8e6e7d38c81283a8ef19ae7a312f4e6f9159d43ccd6224ebff4b

Description hash: sha256:3a88ba1da928b76b7847ea1af938c9955e0f7c686e94d061556fa2d7e68bf304

Interface hash: sha256:5023478eed0beb704122cf1456d09b6420ad1888e620d96cf0f9e526ab1834b3

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/attach_iso_to_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "attach_iso_to_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8293605961f032c753cad81e90ebe8dc0b21a4a682ab442428862df88c4842c0"
}
toolwrite2.5.0No change observed
batch_clone_vmsvmware-skills-vmware-aiops:tool:batch_clone_vms
Observed interface and hashes

[WRITE] Batch clone multiple VMs from a source VM (gold image). Each clone: full copy → optional reconfigure → optional snapshot → optional power on. Returns one dict per VM with its status. Clones run sequentially, so a long vm_names list may take a while — prefer batch_linked_clone_vms for disposable test copies.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cpu": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override CPU count for all clones (optional).",
      "title": "Cpu"
    },
    "memory_mb": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override memory for all clones (optional).",
      "title": "Memory Mb"
    },
    "power_on": {
      "default": false,
      "description": "Power on each clone after creation.",
      "title": "Power On",
      "type": "boolean"
    },
    "snapshot_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Snapshot each clone with this name (optional).",
      "title": "Snapshot Name"
    },
    "source_vm_name": {
      "description": "Source VM to clone from.",
      "title": "Source Vm Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_names": {
      "description": "Names for the new VMs.",
      "items": {
        "type": "string"
      },
      "title": "Vm Names",
      "type": "array"
    }
  },
  "required": [
    "source_vm_name",
    "vm_names"
  ],
  "title": "batch_clone_vmsArguments",
  "type": "object"
}
sha256:0b7c60884d056865b152d3f56b69c7e523d58c71e4321f5d2585f06b218a8916

Output schema

{
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "batch_clone_vmsOutput",
  "type": "object"
}
sha256:774f4d720fef784d7cbdf41eb80660e96ae9015cf1c01f2ea2afb7611307203e

Description hash: sha256:b257db0e0b4a88aa3056873f637fda9456933fa880b16c209cade6ede4ff385d

Interface hash: sha256:3e241d06c4821ae2c5f7deb052a92f52f26eae8b2ba9d78e4bae53a809907e1d

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/batch_clone_vms",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "batch_clone_vms"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:28cd9a5c045371369460dafd2393bf617cd16f9558920f6d1f0a987ab66bf023"
}
toolwrite2.5.0No change observed
batch_deploy_from_specvmware-skills-vmware-aiops:tool:batch_deploy_from_spec
Observed interface and hashes

[WRITE] Deploy multiple VMs in one call from a declarative YAML spec file. Use for fleet provisioning (several VMs, shared defaults); for a single VM prefer deploy_vm_from_template, clone_vm, deploy_vm_from_ova, or deploy_linked_clone. The channel is chosen by spec keys: "source" (full clone), "template", "linked_clone: {source, snapshot}", per-VM "ova", else empty-VM creation (optionally "iso"). A "defaults" block sets cpu/memory_mb/disk_gb/network/ datastore/snapshot/power_on, overridable per VM. VMs deploy sequentially and one VM's failure does not stop the rest. Returns: One dict per VM: name, status ("ok" or "error"), and messages with per-step results.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "spec_path": {
      "description": "Local filesystem path to the deploy.yaml specification file.",
      "title": "Spec Path",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "spec_path"
  ],
  "title": "batch_deploy_from_specArguments",
  "type": "object"
}
sha256:eeb6e782cda0ab5a84aeea84103ae9df4c8f942881ec978f17c240f95ee72730

Output schema

{
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "batch_deploy_from_specOutput",
  "type": "object"
}
sha256:b6eeed892d307d03eef62915939b2109b7765e58ec5556637de53d482fbd1639

Description hash: sha256:69a8d1cac72d46243d85b9b8df6871fc208ba0815023d8085dfc3ea5db139986

Interface hash: sha256:d50d0e9dbc0763cfbdf448b328f78b175eceeac0df3fb09109aaba3d16b0c2a4

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/batch_deploy_from_spec",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "batch_deploy_from_spec"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:23ce078d16cbef6f3e7e2d1f7676093344179ed1ba826998746fce455f5e863d"
}
toolwrite2.5.0No change observed
batch_linked_clone_vmsvmware-skills-vmware-aiops:tool:batch_linked_clone_vms
Observed interface and hashes

[WRITE] Batch create linked clones from a VM snapshot (fastest batch provisioning). Clones share the source disk via copy-on-write, so the source must stay intact. Returns one dict per clone. Prefer batch_clone_vms for independent copies.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "baseline_snapshot": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Snapshot each clone with this name (optional).",
      "title": "Baseline Snapshot"
    },
    "cpu": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override CPU count (optional).",
      "title": "Cpu"
    },
    "memory_mb": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override memory (optional).",
      "title": "Memory Mb"
    },
    "power_on": {
      "default": false,
      "description": "Power on each clone.",
      "title": "Power On",
      "type": "boolean"
    },
    "snapshot_name": {
      "description": "Clone base (from list_vm_snapshots).",
      "title": "Snapshot Name",
      "type": "string"
    },
    "source_vm_name": {
      "description": "Source VM to clone from.",
      "title": "Source Vm Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target from config.",
      "title": "Target"
    },
    "vm_names": {
      "description": "Names for the new linked clones.",
      "items": {
        "type": "string"
      },
      "title": "Vm Names",
      "type": "array"
    }
  },
  "required": [
    "source_vm_name",
    "snapshot_name",
    "vm_names"
  ],
  "title": "batch_linked_clone_vmsArguments",
  "type": "object"
}
sha256:3dd193f4ca7698b788be75db8c095d1de44d56036452931e2e641c14aa50d256

Output schema

{
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "batch_linked_clone_vmsOutput",
  "type": "object"
}
sha256:11105e31e634f8d60125b3db1bc686df840b9dba7eb3380864532123e9cafb5b

Description hash: sha256:30896805f9fd3d1f45b06d2f90973725e086a015e92562da25048f434970a3e4

Interface hash: sha256:060ca7ee13adb48107c9f505003f827b2168969abb36d05c80bfef88c4c7106a

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/batch_linked_clone_vms",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "batch_linked_clone_vms"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f2e99caf5e484e877687ba72e4bea74ab2ebdba478e06e3c61bdb0df31ebac2d"
}
toolwrite2.5.0No change observed
browse_datastorevmware-skills-vmware-aiops:tool:browse_datastore
Observed interface and hashes

[READ] Search a vSphere datastore folder and all its subfolders for files. Use this to find OVA/ISO/VMDK paths before calling deploy_vm_from_ova or attach_iso_to_vm; for an estate-wide image sweep use scan_all_datastore_images. Returns the list envelope: 'items' is one row per file, and 'returned'/'total'/'truncated' state completeness. Every match in the searched folders is returned, so truncated is always false.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "datastore_name": {
      "description": "Name of the datastore to browse.",
      "title": "Datastore Name",
      "type": "string"
    },
    "path": {
      "default": "",
      "description": "Datastore-relative folder to start from (empty string for root); a leading '/' or '..' is refused. The search is recursive, so the root returns matches from every folder; each row's ds_path (\"[ds] dir/file\") can be passed as-is to deploy_vm_from_ova or attach_iso_to_vm.",
      "title": "Path",
      "type": "string"
    },
    "pattern": {
      "default": "*",
      "description": "Glob pattern to filter files (e.g. \"*.ova\", \"*.iso\", \"*\").",
      "title": "Pattern",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    }
  },
  "required": [
    "datastore_name"
  ],
  "title": "browse_datastoreArguments",
  "type": "object"
}
sha256:1713794af6e7a76c8df7282ed1a4933db8721639708049fb25cc828e37086ac3

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:0c0c9aa976ecbf4ca214daf28bc31605011ea07e76481ce687ddcddca3ef7f5e

Interface hash: sha256:5eb3b9ce1afb12a74389c805fafa98ea468e47903c393cf1ea1e2fd2521850e5

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/browse_datastore",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "browse_datastore"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:da62378e7b9c4b3b7e3399a25d95a932a3bbf4b5c7e362250bfccddc9c1d5a0b"
}
toolread2.5.0No change observed
cancel_vm_ttlvmware-skills-vmware-aiops:tool:cancel_vm_ttl
Observed interface and hashes

[WRITE] Cancel an existing TTL for a VM (prevents auto-deletion). Returns a status string. Use list_vm_ttls first for the exact vm_name. This only removes the schedule and never touches the VM itself.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "vm_name": {
      "description": "Name of the VM whose TTL should be cancelled.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "cancel_vm_ttlArguments",
  "type": "object"
}
sha256:c7da3e19bab8735ec07474a8440d0e9558b1fc1d34c943600836105ba722ace3

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "cancel_vm_ttlOutput",
  "type": "object"
}
sha256:6b76958a952e90ab0d77478ba308db545930e3e1d746851ff38cee3d6ad00e8f

Description hash: sha256:927c8111e61701df5184b7de6faa1a84ed6772e38adee8f4f7befdd4b268b569

Interface hash: sha256:e3220838e6479b39ac1178e27c92423f41639376a9f81d2c9dc38c9899eebae8

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/cancel_vm_ttl",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "cancel_vm_ttl"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:6f173c4f885ebb3f3f0ef70b35f032d35a80ef3384701940f2139e5ca4cd0ed2"
}
toolwrite2.5.0No change observed
clone_vmvmware-skills-vmware-aiops:tool:clone_vm
Observed interface and hashes

[WRITE] Clone a VM. Without to_host/to_datastore the clone lands on the source's host+datastore. Returns a status string naming the clone. Full independent copy — slow and full disk cost; prefer deploy_linked_clone for near-instant test copies and batch_clone_vms for many at once. Cloning a running VM may capture a crash-consistent disk.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "new_name": {
      "description": "Name for the new clone.",
      "title": "New Name",
      "type": "string"
    },
    "power_on": {
      "default": false,
      "description": "Power on the clone after creation.",
      "title": "Power On",
      "type": "boolean"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "to_datastore": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Target datastore name (default: source's datastore).",
      "title": "To Datastore"
    },
    "to_host": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Target ESXi host name (default: source's host).",
      "title": "To Host"
    },
    "vm_name": {
      "description": "Source VM (or template) name.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "new_name"
  ],
  "title": "clone_vmArguments",
  "type": "object"
}
sha256:ab533dc737eb38c8638602cf6a76a1ffa8503a7e147e83f622b032928426d987

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "clone_vmOutput",
  "type": "object"
}
sha256:f2cf81629d16b50c7aab75214eed68ee2eb6ee26a78b9d50f611ba3a6dc219b3

Description hash: sha256:db15f149134176b0815e9206887ccbf386f4f262c6e46e9c1c3e0bfe98432ade

Interface hash: sha256:d0c3c82962524dafde4b39f9c6736faf95bd4157eb7664505fd3276af8043d55

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/clone_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "clone_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:c08766257c701b45dd9a2cf99cc9f34cf8ce6ba4aedd26b667672d18968eb087"
}
toolwrite2.5.0No change observed
configure_clustervmware-skills-vmware-aiops:tool:configure_cluster
Observed interface and hashes

[WRITE] Reconfigure cluster HA/DRS settings. Returns a status string naming what changed. Pass only the fields to change; None leaves a setting untouched — then verify with get_cluster_info. drs_behavior applies only when DRS is enabled.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "drs": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Enable (True) or disable (False) DRS, or None to leave unchanged.",
      "title": "Drs"
    },
    "drs_behavior": {
      "anyOf": [
        {
          "enum": [
            "fullyAutomated",
            "partiallyAutomated",
            "manual"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "DRS behavior: \"fullyAutomated\", \"partiallyAutomated\", or \"manual\".",
      "title": "Drs Behavior"
    },
    "ha": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Enable (True) or disable (False) HA, or None to leave unchanged.",
      "title": "Ha"
    },
    "name": {
      "description": "Cluster name.",
      "title": "Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter target name from config.",
      "title": "Target"
    }
  },
  "required": [
    "name"
  ],
  "title": "configure_clusterArguments",
  "type": "object"
}
sha256:e1d5a8e61a8126b4430ac088f5ec6bc66a35a62a728b37ba86bdd71f536ac39f

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "configure_clusterOutput",
  "type": "object"
}
sha256:5ceb60c0fc6a486eb81d095c6173bd008c70e3d433d97b3a96c86a493922329a

Description hash: sha256:21c9a0c9bcd65d0e7c616d5decd915f18f06afc1512c1b8d3e02e9e141d3d838

Interface hash: sha256:1aa4c329a8a6cb6cce072ecc50a9347951ca560ab3e29269224990e9c19a06a4

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/configure_cluster",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "configure_cluster"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5cbd2962df8b97bcd03e2f9cbeecf815a9a09688a92925b42c39ff01fc367125"
}
toolwrite2.5.0No change observed
convert_vm_to_templatevmware-skills-vmware-aiops:tool:convert_vm_to_template
Observed interface and hashes

[WRITE] Convert a powered-off VM to a vSphere template. Returns a status string. Use this to freeze a golden image: afterwards the VM cannot be powered on and serves only as a clone source for deploy_vm_from_template.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Name of the VM to convert (must be powered off).",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "convert_vm_to_templateArguments",
  "type": "object"
}
sha256:1ec8bb9ad5c0642db8f4763b4269d5d2dccb569cdebf4965f6295e896d5c5347

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "convert_vm_to_templateOutput",
  "type": "object"
}
sha256:728d176b5e361539e9b3154be06e862349606371a928c65fd6c9251826ceff67

Description hash: sha256:7ff9b9d922f1d52a4f568d7541a905c22f1a105b7f90df22c64af80b76a505fc

Interface hash: sha256:81bf9183ea988b24346ca7584c2dd792c07d12751acf204f0d569c12f8a9c5b3

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/convert_vm_to_template",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "convert_vm_to_template"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a62d7774f5baf6fbd44589870eb06184210dea6aaef84608be4e77a04ed65b03"
}
toolwrite2.5.0No change observed
create_clustervmware-skills-vmware-aiops:tool:create_cluster
Observed interface and hashes

[WRITE] Create a new empty cluster in a datacenter, optionally enabling HA and DRS. Fails with a clear error (no partial state) if the name already exists or drs_behavior is invalid. Then add hosts with add_cluster_host, change HA/DRS later with configure_cluster, and verify with get_cluster_info. Returns a status string naming the features enabled.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "datacenter": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Datacenter name; omit for the first one on the target.",
      "title": "Datacenter"
    },
    "drs": {
      "default": false,
      "description": "True enables DRS (default False).",
      "title": "Drs",
      "type": "boolean"
    },
    "drs_behavior": {
      "default": "fullyAutomated",
      "description": "\"fullyAutomated\" (default), \"partiallyAutomated\", or \"manual\". Only takes effect when drs=True.",
      "enum": [
        "fullyAutomated",
        "partiallyAutomated",
        "manual"
      ],
      "title": "Drs Behavior",
      "type": "string"
    },
    "ha": {
      "default": false,
      "description": "True enables vSphere HA (default False).",
      "title": "Ha",
      "type": "boolean"
    },
    "name": {
      "description": "Name for the new cluster; must be unique in the datacenter.",
      "title": "Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target from config.yaml; omit for the default target.",
      "title": "Target"
    }
  },
  "required": [
    "name"
  ],
  "title": "create_clusterArguments",
  "type": "object"
}
sha256:2ab2c14a442f322d6d1032a8fe2ca43352ac174fdb2aa273ad53eeb690cce35a

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "create_clusterOutput",
  "type": "object"
}
sha256:c64706a0beb85709bbba79cba8088c04aecbe5a51f0d1940fb4d6f355e96d3e9

Description hash: sha256:3ca01708ecba75bcd9960a05258852d4de49761b225b85b709cb4b67079f11b0

Interface hash: sha256:9fe98d8f9e4bbdab4252456b6642dd8db06c5f32fdd4b0e8171e62f6602bb899

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/create_cluster",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "create_cluster"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a3a9b8a7aa29e5e063b084ab1807a187d8eb66d574a98416516c4f2796bb9cbe"
}
toolwrite2.5.0No change observed
create_drs_rulevmware-skills-vmware-aiops:tool:create_drs_rule
Observed interface and hashes

[WRITE] Create a VM-VM DRS rule (affinity or anti-affinity) - preview/confirm gated. rule_type "affinity" keeps the listed VMs together; "antiAffinity" keeps them apart (e.g. redundant appliance pairs on separate hosts). Requires >=2 distinct VMs, all members of the cluster. VM-Host rules hang off cluster VM/host groups and are not created here. Verify with list_drs_rules. Audited. Returns: Preview dict (action="preview", would_create) or result dict (action="created", created incl. the assigned key). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster": {
      "description": "Exact cluster name.",
      "title": "Cluster",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True creates it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "enabled": {
      "default": true,
      "description": "Create the rule enabled (default) or disabled.",
      "title": "Enabled",
      "type": "boolean"
    },
    "rule_name": {
      "description": "Name for the new rule; must be unique on the cluster.",
      "title": "Rule Name",
      "type": "string"
    },
    "rule_type": {
      "description": "\"affinity\" or \"antiAffinity\".",
      "enum": [
        "affinity",
        "antiAffinity"
      ],
      "title": "Rule Type",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "vm_names": {
      "description": "VM names the rule governs (>=2, all in the cluster).",
      "items": {
        "type": "string"
      },
      "title": "Vm Names",
      "type": "array"
    }
  },
  "required": [
    "cluster",
    "rule_name",
    "rule_type",
    "vm_names"
  ],
  "title": "create_drs_ruleArguments",
  "type": "object"
}
sha256:4c8696a87b15aa83a2d4b3138c417005fe39c6fbb0528cba69a63a147b71badb

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b445b40361c827dc7a4a7f940c6ca8145d6c8117943ee0924fa57a9e1570c4c9

Interface hash: sha256:0876f794571592a204730dda831e3fb0000aeaf84d3b3daf3635b09c80906db7

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/create_drs_rule",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "create_drs_rule"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2af676c75dbe79b1c5000aa60b5a02a003ed8aef4f876aae5e939c7a4e78cd88"
}
toolwrite2.5.0No change observed
create_dvs_portgroupvmware-skills-vmware-aiops:tool:create_dvs_portgroup
Observed interface and hashes

[WRITE] Create a VLAN-tagged portgroup on a dvSwitch - preview/confirm gated. confirm=False (default) validates everything (switch exists, name free, binding and VLAN legal) and returns the exact spec that WOULD be created without writing anything. confirm=True creates the portgroup and waits for the task. Verify afterwards with list_dvs_portgroups. Audited. binding="ephemeral" creates a portgroup with no pre-created port pool, attachable from the ESXi host client even when vCenter is down - use for a self-hosted VCSA's own management portgroup. num_ports is ignored for ephemeral. lateBinding is deprecated by vSphere and not offered. Returns: Preview dict (action="preview", would_create) or result dict (action="created", created). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "binding": {
      "default": "earlyBinding",
      "description": "\"earlyBinding\" (default) or \"ephemeral\".",
      "enum": [
        "earlyBinding",
        "ephemeral"
      ],
      "title": "Binding",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True creates it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "dvs_name": {
      "description": "Name of the distributed virtual switch to create it on.",
      "title": "Dvs Name",
      "type": "string"
    },
    "name": {
      "description": "Name for the new portgroup; must be unique on the switch.",
      "title": "Name",
      "type": "string"
    },
    "num_ports": {
      "default": 8,
      "description": "Port count for earlyBinding portgroups (default 8).",
      "title": "Num Ports",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "vlan_id": {
      "description": "VLAN ID to tag (0-4094; 0 = none).",
      "title": "Vlan Id",
      "type": "integer"
    }
  },
  "required": [
    "name",
    "dvs_name",
    "vlan_id"
  ],
  "title": "create_dvs_portgroupArguments",
  "type": "object"
}
sha256:2cfc274236be37ca49763f445657e84b23b4fe89322be57080883ebd7f6aaff6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:16674c36c561e15b9dcd87ed017d68544944263e9d59a9a3b444a0cecef74be0

Interface hash: sha256:4c3748fbadfbf8a16a4449e27614f73d5b846c7ffbdc8d29dd6882c8ec76f27f

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/create_dvs_portgroup",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "create_dvs_portgroup"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e97f32d2f3a2746407aba40cfeab293178b33c64d2e72c7c728d58a324dde39e"
}
toolwrite2.5.0No change observed
create_vmvmware-skills-vmware-aiops:tool:create_vm
Observed interface and hashes

[WRITE] Create a new empty VM with the given hardware sizing. Creates a powered-off VM with one disk (none when disk_gb=0) and one NIC. To populate it, attach an ISO (attach_iso_to_vm) and power it on, or use deploy_vm_from_ova or clone_vm for a ready-to-run guest. Fails before creating anything if the datastore is not found. If the create task fails and datastore_name was given, an empty VM directory it provably left is removed; otherwise the error names what to check. Returns a status string with the new VM name.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cpu": {
      "default": 2,
      "description": "vCPU count (default 2).",
      "title": "Cpu",
      "type": "integer"
    },
    "datastore_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Target datastore; omit for the first accessible one.",
      "title": "Datastore Name"
    },
    "disk_gb": {
      "default": 40,
      "description": "Primary disk size in GB, 0-65536 (default 40); 0 creates no disk.",
      "title": "Disk Gb",
      "type": "integer"
    },
    "folder_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter folder path; omit for the datacenter root.",
      "title": "Folder Path"
    },
    "memory_mb": {
      "default": 4096,
      "description": "Memory in MB (default 4096).",
      "title": "Memory Mb",
      "type": "integer"
    },
    "network_name": {
      "default": "VM Network",
      "description": "Port group for the NIC (default \"VM Network\").",
      "title": "Network Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target from config.yaml; omit for the default.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Name for the new VM; must not already exist.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "create_vmArguments",
  "type": "object"
}
sha256:d7de30f6436dd5942c4bebe087f126445afd1444a137438c11f5eee2ca8543e0

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "create_vmOutput",
  "type": "object"
}
sha256:f985e8f74d7e5bebcc4100b73521e0d84e485a28061262ed5a91bc7c6564d412

Description hash: sha256:3d4898ae1dd24544a8091c3550fd80844e5dce87f8b7faff4cb308f27400a830

Interface hash: sha256:43f1102b13aa2cd17f6b08b200a5805ef741fb6f75946083d4e33228bb488bfb

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/create_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "create_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:bcde506f5f045bb53fdeadddcd74b9a8952d22ab499e3f88c0d2c4c9179e91f8"
}
toolwrite2.5.02.5.1
create_vm_planvmware-skills-vmware-aiops:tool:create_vm_plan
Observed interface and hashes

[WRITE] Create an execution plan for multi-step VM operations. Use for 2+ steps or 2+ VMs. Validates actions, checks the targets exist in vSphere, and generates a plan with rollback info per step. Each operation is a dict with "action" key plus action-specific params. Allowed actions: power_on, power_off, reset, suspend, create_vm, delete_vm, reconfigure, create_snapshot, delete_snapshot, revert_snapshot, clone, migrate, deploy_ova, deploy_template, linked_clone, attach_iso, convert_to_template. Returns plan dict with plan_id, steps, summary (vms_affected, irreversible_steps, rollback_available). Show to user for confirmation before calling apply_vm_plan.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "operations": {
      "description": "List of operation dicts, each with \"action\" + params.",
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Operations",
      "type": "array"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    }
  },
  "required": [
    "operations"
  ],
  "title": "create_vm_planArguments",
  "type": "object"
}
sha256:5af31c6215b706fd5d0ad7cafd5e7f254924dc0512c012421170d230930faa68

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:a75d7affe49a64732d5bb4669114f05cda68df499368e5f0f071ee3dfda41f22

Interface hash: sha256:7e30511682bd11da583e8f2a9fd0b4dd0c3f8a778d3062d5092004585efc37ec

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/create_vm_plan",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "create_vm_plan"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:6d04f47f60706c18738d903eb41b6c1142a6c6aadb7eb4d10ad94c53956de681"
}
toolwrite2.5.0No change observed
create_vm_snapshotvmware-skills-vmware-aiops:tool:create_vm_snapshot
Observed interface and hashes

[WRITE] Create a snapshot of a VM. Returns a status string. Use this before a risky change so revert_vm_snapshot can undo it, then reclaim the space with delete_vm_snapshot — snapshots left for days grow delta disks and must not be treated as backups.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "description": {
      "default": "",
      "description": "Optional description.",
      "title": "Description",
      "type": "string"
    },
    "memory": {
      "default": false,
      "description": "Include memory state (heavier, allows resume).",
      "title": "Memory",
      "type": "boolean"
    },
    "quiesce": {
      "default": false,
      "description": "Quiesce guest filesystem (requires running VMware Tools).",
      "title": "Quiesce",
      "type": "boolean"
    },
    "snapshot_name": {
      "description": "Snapshot name.",
      "title": "Snapshot Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_name": {
      "description": "VM to snapshot.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "snapshot_name"
  ],
  "title": "create_vm_snapshotArguments",
  "type": "object"
}
sha256:7c33e6e708a50bfdfab4ee23c3898ec3c61b779c82e7b3ead7415c73068c9713

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "create_vm_snapshotOutput",
  "type": "object"
}
sha256:eaa23588737194cc1b4141604f6ce5527d9ad70d27a60357143d2d629107a914

Description hash: sha256:86bd4c84a1c9d3bd4ae8be44b5b0f86e2a4e9301c333747a1589a2db2be30c83

Interface hash: sha256:1aec238c8925cd89c179c7b7e0d74cdf8ed562d3a68c0ef4597573317b2246df

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/create_vm_snapshot",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "create_vm_snapshot"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e9cd3560edd3028bce3368cf932447f835d47905af8f5cc810d956767fc63418"
}
toolwrite2.5.0No change observed
delete_clustervmware-skills-vmware-aiops:tool:delete_cluster
Observed interface and hashes

[WRITE] Delete an empty cluster (no hosts must remain). Without confirm=True this only previews: it returns blast_radius (cluster name and id, host/VM/datastore counts and names, blockers) and deletes nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused: a cluster that still has hosts or VMs (evacuate members with remove_cluster_host first), or one whose members could not be read. Check get_cluster_info first. Returns a dict (action, blast_radius).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "name": {
      "description": "Name of the cluster to delete.",
      "title": "Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter target name from config.",
      "title": "Target"
    }
  },
  "required": [
    "name"
  ],
  "title": "delete_clusterArguments",
  "type": "object"
}
sha256:67ee62a8c71187faa76266ef0c8047325aaf96ba9fb6f4c7480ef81d6da28c1b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ee5b692021ca1382f7fec238f17cc5f5197f2effc6f80a3c5c3499ebb08cc042

Interface hash: sha256:5ac1145829bf269cff2f29462c3dc7c18eefd1f09f43747089b7080e050b882f

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/delete_cluster",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "delete_cluster"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:393d5c954fffa6e18ae012115b2897c5473dfc415d3649f91eafa4670e8fad80"
}
tooldestructive2.5.0No change observed
delete_drs_rulevmware-skills-vmware-aiops:tool:delete_drs_rule
Observed interface and hashes

[WRITE] Delete a VM-VM DRS rule - confirm-gated, guarded. REFUSES non-VM-VM rules: VM-Host rules can carry licensing/compliance placement constraints (must-run-on licensed hosts) and hang off cluster groups - manage those in the vSphere UI. The preview and result both record the full rule definition so a mistaken delete can be recreated from the audit trail. Audited. Returns: Preview dict (action="preview", would_delete) or result dict (action="deleted", deleted). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster": {
      "description": "Exact cluster name.",
      "title": "Cluster",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True deletes it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "rule_name": {
      "description": "Exact rule name (see list_drs_rules).",
      "title": "Rule Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "cluster",
    "rule_name"
  ],
  "title": "delete_drs_ruleArguments",
  "type": "object"
}
sha256:75970a9618f2ab384db4160b62aeeddba53223c4a0415bb0fc3cf1be2b922de8

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:8f2a9d9a59dbff18dbb5dddde0bd5f726dabb0762d0360e516d0ea8c3df4988f

Interface hash: sha256:11c39dfe893dbbef478d8a79d043defe819e8a057593c16609dd4e7cb97037d1

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/delete_drs_rule",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "delete_drs_rule"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:09384589aa74ea2df9ce1b07cb799ece975eefd5ec72ed1437a229b32d32acc5"
}
tooldestructive2.5.0No change observed
delete_vmvmware-skills-vmware-aiops:tool:delete_vm
Observed interface and hashes

[WRITE] Delete a VM and its disks and snapshots (irreversible). Without confirm=True this only previews: it returns blast_radius (identity, host, disks, total size, snapshot count, blockers) and destroys nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user said "delete" earlier: they have not seen what it destroys yet. To delete, call again with confirm=True and acknowledge_blast_radius set to the preview's acknowledge_with object, unchanged. The VM is re-measured first; if it changed (another snapshot, a different VM under the same name), nothing is deleted and you must preview again. Refused outright: a powered-on or suspended VM (power it off with power_off_vm first), a VM whose disks or identity cannot be read, and a name that matches more than one VM. Use set_vm_ttl instead when the VM should only expire later.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "acknowledge_blast_radius": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The preview's acknowledge_with object.",
      "title": "Acknowledge Blast Radius"
    },
    "confirm": {
      "default": false,
      "description": "False (default) previews; True deletes, with the acknowledgement.",
      "title": "Confirm",
      "type": "boolean"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact name of the VM to delete.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "delete_vmArguments",
  "type": "object"
}
sha256:7f9d8ac5d555893bb4a32ba4a238718b254a0cca39cfa91fbb85ee4ebe76732c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:25c40b8cea7778300b4ed0a0fac250d48cd5fadd77892593194b2fde71f50ac5

Interface hash: sha256:bc148db3b018b1f5968068427f551fc3f893117a41ffe44c36b5dde991f8b6ce

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/delete_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "delete_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e623f95f2dd16fa87fdd42ad392494118be9c0e6777d3e9ebc48727a651e8e6a"
}
tooldestructive2.5.0No change observed
delete_vm_snapshotvmware-skills-vmware-aiops:tool:delete_vm_snapshot
Observed interface and hashes

[WRITE] Permanently delete a named snapshot, consolidating its delta disk into the parent. Without confirm=True this only previews: it returns blast_radius (VM and instance UUID, the snapshot's name, id and creation time, remove_children, how many child snapshots sit below it and how many snapshots would be removed) and deletes nothing. Show it to the user and get their decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Frees disk space and does NOT change the VM's current state (unlike revert_vm_snapshot). Works while the VM is powered on. Refused: a snapshot name that is not found, a name that matches more than one snapshot on the VM (vSphere allows duplicates; rename one first), and a snapshot tree that cannot be read. Run list_vm_snapshots first for exact names. Consolidation is slow for old/large deltas (often minutes). By default (wait=False) this returns a task id immediately so it does not block your context — poll it with get_vm_task_status. Set wait=True only for small snapshots (blocks up to 30 min). Returns: Dict with action (preview, snapshot_delete_started, snapshot_deleted), blast_radius, and result (carries the task id to poll via get_vm_task_status).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "remove_children": {
      "default": false,
      "description": "False (default) = children are kept and consolidated; True = delete the entire snapshot subtree below this one as well.",
      "title": "Remove Children",
      "type": "boolean"
    },
    "snapshot_name": {
      "description": "Exact snapshot name from list_vm_snapshots output.",
      "title": "Snapshot Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target from config.yaml; omit for the default target.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact name of the VM owning the snapshot.",
      "title": "Vm Name",
      "type": "string"
    },
    "wait": {
      "default": false,
      "description": "False (default) = async, return task id at once; True = block.",
      "title": "Wait",
      "type": "boolean"
    }
  },
  "required": [
    "vm_name",
    "snapshot_name"
  ],
  "title": "delete_vm_snapshotArguments",
  "type": "object"
}
sha256:3060e34adbe4b3a6fd117de879437fbf5d7394e59db6c4b47b249f1a70c6de2d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c7c264ad688567c8df8344299c559ca824e471ca9b4d144bf61e4bb1d7786d37

Interface hash: sha256:cb061e0e3c139d32aea5915911d4f371c0c01eddb61f59c5e796d3a941692245

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/delete_vm_snapshot",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "delete_vm_snapshot"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:1d27db25f0e9c24384d6d27b4b2b81ac7c8ba507c21ef52bcf39cd1cce60355b"
}
tooldestructive2.5.0No change observed
deploy_linked_clonevmware-skills-vmware-aiops:tool:deploy_linked_clone
Observed interface and hashes

[WRITE] Create a linked clone from a VM snapshot — near-instant, minimal disk usage. The clone writes to a copy-on-write delta over the source's base disk, so it depends on the source staying intact. Fastest provisioning for test/dev fleets; use clone_vm for fully independent copies. Requires the named snapshot — run list_vm_snapshots first. Returns a status string with the new clone name.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "baseline_snapshot": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "If set, snapshots the new clone with this name.",
      "title": "Baseline Snapshot"
    },
    "cpu": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override vCPU count; omit to keep the source's value.",
      "title": "Cpu"
    },
    "memory_mb": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override memory in MB; omit to keep the source's value.",
      "title": "Memory Mb"
    },
    "new_name": {
      "description": "Name for the new linked clone; must not already exist.",
      "title": "New Name",
      "type": "string"
    },
    "power_on": {
      "default": false,
      "description": "Power the clone on after creation (default False).",
      "title": "Power On",
      "type": "boolean"
    },
    "snapshot_name": {
      "description": "Clone base (from list_vm_snapshots).",
      "title": "Snapshot Name",
      "type": "string"
    },
    "source_vm_name": {
      "description": "Source VM name (must have at least one snapshot).",
      "title": "Source Vm Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target from config.yaml; omit for the default.",
      "title": "Target"
    }
  },
  "required": [
    "source_vm_name",
    "snapshot_name",
    "new_name"
  ],
  "title": "deploy_linked_cloneArguments",
  "type": "object"
}
sha256:2fcf040ff2dfc54dfcf8991bc2f2b62147184ab0bd624fb86d9228de1f8c6431

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "deploy_linked_cloneOutput",
  "type": "object"
}
sha256:56cf5fba17c2a862b96e0d391de81f727a0a947e51217f04ff84f21d1710da5d

Description hash: sha256:dbe4a267463aa67519d22cd28789611058a5adc4d2e5ac0a3e3b7bd10e3c3e91

Interface hash: sha256:9ff0170c45aac29cfea552fd9f8e0a2a7e4ba8d817f81f03ec799d895f1f4787

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/deploy_linked_clone",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "deploy_linked_clone"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e659fa4f5f37aff736dc12dab318d4de55563616862ac365719e86d673c1cba5"
}
toolwrite2.5.0No change observed
deploy_vm_from_ovavmware-skills-vmware-aiops:tool:deploy_vm_from_ova
Observed interface and hashes

[WRITE] Create a new VM by importing a local .ova file (OVF parse + VMDK upload). Use for local OVA files; for vSphere templates use deploy_vm_from_template, to copy an existing VM clone_vm. Returns a status string naming the new VM. Upload time scales with OVA size; fails before creating anything if the datastore is not found.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "datastore_name": {
      "description": "Target datastore (see browse_datastore).",
      "title": "Datastore Name",
      "type": "string"
    },
    "folder_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter folder path; omit for the datacenter root.",
      "title": "Folder Path"
    },
    "network_name": {
      "default": "VM Network",
      "description": "Port group every network in the OVF is mapped to (default \"VM Network\"). Refused before anything is imported if no network, or more than one, has this name in the datacenter.",
      "title": "Network Name",
      "type": "string"
    },
    "ova_path": {
      "description": "Local path to the .ova file (must be readable by this server).",
      "title": "Ova Path",
      "type": "string"
    },
    "power_on": {
      "default": false,
      "description": "Power the VM on after import (default False).",
      "title": "Power On",
      "type": "boolean"
    },
    "snapshot_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "If set, snapshots the new VM with this name.",
      "title": "Snapshot Name"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target from config.yaml; omit for the default.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Name for the new VM; must not already exist.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "ova_path",
    "vm_name",
    "datastore_name"
  ],
  "title": "deploy_vm_from_ovaArguments",
  "type": "object"
}
sha256:ef8b3fe1f38992cf6db4df76ef64dd73d8755b098f1d4b971c028def25613901

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "deploy_vm_from_ovaOutput",
  "type": "object"
}
sha256:6ca7dd7ea42b366b6320ba3547baedb99689b7820f7e34a27403029e7ef6cdc5

Description hash: sha256:a8df2465acaec4ce986a380d21413cc99b22ba4afa48e60f35e17b6e73fdb6cf

Interface hash: sha256:f13ed2f58f1821c923198126fab0bfdf8357bdb367a33b2ae25526a762d38928

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/deploy_vm_from_ova",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "deploy_vm_from_ova"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:350250c4599ac853ccb984c959b3ec050ea906046d64b12a5d7c91ff060dc63d"
}
toolwrite2.5.0No change observed
deploy_vm_from_templatevmware-skills-vmware-aiops:tool:deploy_vm_from_template
Observed interface and hashes

[WRITE] Deploy a new VM by cloning from a vSphere template. Returns a status string. Use for VMs marked as templates; for a running source VM use clone_vm. Requires an existing template — convert_vm_to_template makes one.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cpu": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override CPU count (optional).",
      "title": "Cpu"
    },
    "datastore_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Target datastore (template's own if omitted).",
      "title": "Datastore Name"
    },
    "memory_mb": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Override memory in MB (optional).",
      "title": "Memory Mb"
    },
    "new_name": {
      "description": "Name for the new VM.",
      "title": "New Name",
      "type": "string"
    },
    "power_on": {
      "default": false,
      "description": "Power on after deployment.",
      "title": "Power On",
      "type": "boolean"
    },
    "snapshot_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Snapshot the new VM with this name.",
      "title": "Snapshot Name"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target from config.",
      "title": "Target"
    },
    "target_host": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "ESXi host to place the VM on (list_esxi_hosts); omit to use the template's host and its resource pool.",
      "title": "Target Host"
    },
    "template_name": {
      "description": "Source vSphere template name.",
      "title": "Template Name",
      "type": "string"
    }
  },
  "required": [
    "template_name",
    "new_name"
  ],
  "title": "deploy_vm_from_templateArguments",
  "type": "object"
}
sha256:c1b322fb637d80da90dc10cfb83c1b150cfed2f34ec88f6eded764778f1ebd09

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "deploy_vm_from_templateOutput",
  "type": "object"
}
sha256:979f2a7bc28be322aef5fe239178e97a8bc5ad35530ffa7e78c58b75754ab2f5

Description hash: sha256:f2ced8cebbd2e4249d1bc6cd93902ae96f3ebf7eea479bb222cb18fb32a86386

Interface hash: sha256:b7cfb349e5c8a3ab371932191a1796d09b727166640e19d9a03e200f76f75eb4

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/deploy_vm_from_template",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "deploy_vm_from_template"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:59ea9716af201f170786295d1f42a9ee2afbe0dea1672fe8276c6ec2fe47a6ce"
}
toolwrite2.5.0No change observed
download_vm_guest_filevmware-skills-vmware-aiops:tool:download_vm_guest_file
Observed interface and hashes

[WRITE] Download a file from a VM and write it to a local path. Reads from the guest, writes the local filesystem — the write is why this is not a read tool. Returns a status string. Requires VMware Tools running in the guest OS. Use upload_vm_guest_file for the reverse direction; to capture command output use run_vm_guest_command_with_output instead — it redirects and downloads for you. Refuses a destination that already exists unless overwrite=True, and never writes through a symlink or over a directory. Pick a path that does not exist yet rather than passing overwrite=True by default.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "guest_path": {
      "description": "File path inside the guest to download.",
      "title": "Guest Path",
      "type": "string"
    },
    "local_path": {
      "description": "Local destination path, including the file name.",
      "title": "Local Path",
      "type": "string"
    },
    "overwrite": {
      "default": false,
      "description": "True replaces an existing file at local_path (default False).",
      "title": "Overwrite",
      "type": "boolean"
    },
    "password": {
      "default": "",
      "description": "Guest OS password.",
      "title": "Password",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "username": {
      "description": "Guest OS account to run as. Required — there is no default, so a call can never act as root without choosing root.",
      "title": "Username",
      "type": "string"
    },
    "vm_name": {
      "description": "Target VM name.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "guest_path",
    "local_path",
    "username"
  ],
  "title": "download_vm_guest_fileArguments",
  "type": "object"
}
sha256:043511aac2a42bdb81088e1335ba45dac5ba775cf27378b8eb0b41b516736df7

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "download_vm_guest_fileOutput",
  "type": "object"
}
sha256:5f26a865540bc4b2a57891e3245812576cdb107966a1e0f7b55e138f43c7e3ea

Description hash: sha256:00ada01daaa6e7201cf05dbb45e95415e20f15ecba39246fb49a0d1edce5e3e5

Interface hash: sha256:aa57acd1b6daa214a8f628d284ce2426bba5d75e1c052eb246d414a3e708d343

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/download_vm_guest_file",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "download_vm_guest_file"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:58379b1d63a5450faaeb252f3bff000f48617e7c17c8ed0ca0562f7a8db5ffb6"
}
toolwrite2.5.0No change observed
get_access_infovmware-skills-vmware-aiops:tool:get_access_info
Observed interface and hashes

[READ] The account this server uses on a target, and whether it holds a tool's privileges. When to use: a tool failed with NoPermission, or before a write you want to know the configured account may run. Ask about one ``tool`` (e.g. clone_vm), or omit it to sort every tool of this server into granted / not granted / undetermined. What it returns: {target, account, checked_on, privileges {id: state}, and either ``tool`` {name, requires, verdict, meaning, missing_at_root} or the tools_* lists}, plus the account's direct permissions (role, on, propagate). Gotchas: privileges are checked on the vCenter/ESXi **root folder** only. ``not_granted_at_root`` does not mean no access — a permission on a cluster, folder or VM still lets the tool work there. ``undetermined`` means the platform did not answer, or the tool's deciding permission is not a vSphere privilege (ping_from_vmk); it is never to be read as granted. Changes nothing.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config. Uses default if omitted.",
      "title": "Target"
    },
    "tool": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "A tool name on this server, e.g. clone_vm (None = all tools).",
      "title": "Tool"
    }
  },
  "title": "get_access_infoArguments",
  "type": "object"
}
sha256:108bf3c24b2b87b41ea09a33fe2e0031141231ef70208127550f2a70518d6db3

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:dafc610d4341b4563f59a1c63d949f9df1fbdc34b0db0a2a6b3ee215ca48af06

Interface hash: sha256:ccfab6ff57e45518ee396470ef2f53c36290ab9af82b8d56b999853eba0cd95b

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/get_access_info",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "get_access_info"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f8d62401269da75c7560d289a6ea6c5b0b99e0f0ebb4348138e50aeef0133fa0"
}
toolread2.5.0No change observed
get_cluster_health_summaryvmware-skills-vmware-aiops:tool:get_cluster_health_summary
Observed interface and hashes

[READ] One-glance health rollup for every cluster — "is anything on fire?". Aggregates hosts, VM power state, live CPU/memory pressure, triggered alarms and datastores thin-provisioned past 100% of capacity per cluster, assigns each a status ("ok"/"warn"/"critical"), and flattens the anomalies into a ranked ``top_issues`` focus list — the fast triage view for "what's wrong right now?". Read-only (delegates to the vmware-monitor library). Use it FIRST for a cross-cluster glance, then drill in with investigate_vm or investigate_host. Returns {totals, top_issues, issues_total, clusters, snapshot, customization_hint}. Lead with ``top_issues`` (worst first, each with a drill-down hint), ``clusters`` as context, ``customization_hint`` last. Point-in-time — no trending.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster_filter": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Case-insensitive substring to show only matching clusters.",
      "title": "Cluster Filter"
    },
    "include_vms": {
      "default": true,
      "description": "Roll up VM power counts (default True). False skips the VM pass on very large fleets.",
      "title": "Include Vms",
      "type": "boolean"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config. Uses default if omitted.",
      "title": "Target"
    },
    "top_n": {
      "default": 10,
      "description": "Cap the top_issues focus list (default 10; 0 hides it).",
      "title": "Top N",
      "type": "integer"
    }
  },
  "title": "get_cluster_health_summaryArguments",
  "type": "object"
}
sha256:75c0d249675a889de42049ac9b038d1016af95b93f64efd00f41e6d3a0c24016

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:01f1f1b07591fe64b6f507c5297250030b84e350451799c6a4d1e14c7ecbca2f

Interface hash: sha256:c8c6bbb853b54766b6ad7b148fbd4c3bb6aa26de938df4472a3c6a33d9fae5a8

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/get_cluster_health_summary",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "get_cluster_health_summary"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5db303f7e0c94c2c6313e5ab11535f4226fea2e38c9e54c5927632327fc99988"
}
toolread2.5.0No change observed
get_cluster_infovmware-skills-vmware-aiops:tool:get_cluster_info
Observed interface and hashes

[READ] Get detailed cluster information: member hosts, HA/DRS config, resource capacity. Read-only, no side effects. Use before add_cluster_host / remove_cluster_host (shows membership and per-host maintenance mode) and to verify configure_cluster changes. Returns: Dict with name, host_count, hosts (each: name, connection_state, power_state, maintenance_mode), ha_enabled, ha_admission_control, drs_enabled, drs_behavior, total/effective CPU (MHz) and memory (GB). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "name": {
      "description": "Exact cluster name.",
      "title": "Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "name"
  ],
  "title": "get_cluster_infoArguments",
  "type": "object"
}
sha256:80a80d49f819c49af7a1083559b7235bf16384b84870792daa9078fcbe711350

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:563c0ac8e0909d20ef2a3009268e2cc537a3bcdfe1bc38dd14298153715988e3

Interface hash: sha256:74730e5576f0dddb60f58cc1a988e877c819ef33f5ea4ec9699395a9825731fa

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/get_cluster_info",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "get_cluster_info"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a1063be50ccf4cfc3975ca33cab99f387a8b613472ecb77a5f1b93bfc9a0ef3e"
}
toolread2.5.0No change observed
get_cross_vcenter_attentionvmware-skills-vmware-aiops:tool:get_cross_vcenter_attention
Observed interface and hashes

[READ] "What needs attention now?" across EVERY configured vCenter — one list. Runs get_cluster_health_summary against every configured target and returns one globally ranked ``top_issues`` list (worst first, each tagged with its ``vcenter``) plus a per-target rollup — "where do I look first, anywhere in the estate?". Degrades gracefully: an unreachable target is listed under ``unreachable`` and the rest still aggregate, but it is never counted as healthy: ``totals.worst_status`` is at least ``warn`` (``critical`` when no target answered) and ``totals.status_reason`` says why. Delegates to the vmware-monitor library (read-only). Lead with ``top_issues``, then drill in with investigate_vm. Point-in-time.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster_filter": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Case-insensitive cluster substring applied to every target.",
      "title": "Cluster Filter"
    },
    "top_n": {
      "default": 10,
      "description": "Cap the merged top_issues focus list (default 10).",
      "title": "Top N",
      "type": "integer"
    }
  },
  "title": "get_cross_vcenter_attentionArguments",
  "type": "object"
}
sha256:034f9af25c8cd30bb5c19f032f4f828dd5988f8def63eb6cf21846aa3d06d51d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:37beb5379feaa6ce333a124a0a9f4087774d50ae8317c6147bc2aa1515fefbe4

Interface hash: sha256:e78d1ff3cbada27b8e2fc15894327f394921cb9adb2c687b6ea777bd9bf2d396

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/get_cross_vcenter_attention",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "get_cross_vcenter_attention"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0c613d90f6595f637a5b4cfe16c117bc49c3a0f2c0202d718cd1a046528e0627"
}
toolread2.5.0No change observed
get_vm_task_statusvmware-skills-vmware-aiops:tool:get_vm_task_status
Observed interface and hashes

[READ] Poll a long-running vSphere task by its id (from an async delete_vm_snapshot). Use after delete_vm_snapshot returns a task id, instead of re-running the delete. Returns state (queued/running/success/error/gone), progress percent, and the entity name. 'gone' means vCenter does not know the id: the task finished and was garbage-collected, or the id is wrong. It says nothing about success — re-list the resource to confirm the final state. A failed task reports its fault under 'task_error'; a top-level 'error' key would mean this poll itself failed. Returns: Dict with task_id, state, progress_pct, operation, entity, and task_error/note when relevant.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "task_id": {
      "description": "The task id string returned by an async write operation.",
      "title": "Task Id",
      "type": "string"
    }
  },
  "required": [
    "task_id"
  ],
  "title": "get_vm_task_statusArguments",
  "type": "object"
}
sha256:49b62b2aae031a569d21ecc082fc65a7f2ca10740966227b15f293567deae467

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:83aa3db334bdf0392dbf5f74061537de8dab34f180e56900ef6b10ce0325fae7

Interface hash: sha256:525db2764c74ea0790a810bf39e7aa47108db377d2fe0f15b41b358d966fdfc9

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/get_vm_task_status",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "get_vm_task_status"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f32df5feece42d7e66ce743504fb2d03989b6517d188f11e525593302c8c86d7"
}
toolread2.5.0No change observed
investigate_datastorevmware-skills-vmware-aiops:tool:investigate_datastore
Observed interface and hashes

[READ] "What is happening around this datastore?" — one correlated drill-down. Correlates a datastore's capacity/free space/accessibility, the hosts that mount it, a rollup of the VMs it backs, alarms across datastore/host, and a merged **event timeline**. Delegates to the vmware-monitor library (read-only); do not dump the result raw. (Per-datastore latency is a separate perf report.) Use this AFTER get_cluster_health_summary flags storage pressure. Point-in-time.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "datastore_name": {
      "description": "Exact datastore name. Unknown names return a teaching error.",
      "title": "Datastore Name",
      "type": "string"
    },
    "hours": {
      "default": 24,
      "description": "Event-timeline look-back window in hours (default 24).",
      "title": "Hours",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config (default if omitted).",
      "title": "Target"
    }
  },
  "required": [
    "datastore_name"
  ],
  "title": "investigate_datastoreArguments",
  "type": "object"
}
sha256:fd386bc8b073bc59313c455a103d29dc9b71d0efcde9d4619be99e445fdea7c9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:beb4a1fff40cdd0d4683e885b534c7f471e970d2cb266bf9a8e5aef603f97218

Interface hash: sha256:42bf3c474552e361a065f5f5607c46fee74ccda5ca19f950572fd9bc582fda27

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/investigate_datastore",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "investigate_datastore"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f1c1b1386a7101c74caf65c0c1eea670f4fe003f87aec439cbbb133aa6f29116"
}
toolread2.5.0No change observed
investigate_hostvmware-skills-vmware-aiops:tool:investigate_host
Observed interface and hashes

[READ] "What is happening around this ESXi host?" — one correlated drill-down. Correlates a host's state (connection, CPU/memory, ESXi version, uptime), its cluster context, a rollup of the VMs it runs, the datastores it mounts, alarms across host/cluster/datastore, live performance, and a merged **event timeline**. Delegates to the vmware-monitor library (read-only); do not dump the result raw. Use this AFTER get_cluster_health_summary flags a host. Point-in-time.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "host_name": {
      "description": "Exact host name. Unknown names return a teaching error.",
      "title": "Host Name",
      "type": "string"
    },
    "hours": {
      "default": 24,
      "description": "Event-timeline look-back window in hours (default 24).",
      "title": "Hours",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config (default if omitted).",
      "title": "Target"
    }
  },
  "required": [
    "host_name"
  ],
  "title": "investigate_hostArguments",
  "type": "object"
}
sha256:67cc06ad5db54fa8d268e7a40ff257eb602a50c83078e8641b8dc4ab34b65957

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:9a0a586710a2fee8fc75807b99727f5df98786157209e7e60d9a72be53f16acb

Interface hash: sha256:809a4d882838b7a5eec6fffa4f4b6bfbe92f209a856de65ba5d5dbe8e5f92322

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/investigate_host",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "investigate_host"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:dc70148eabad4a99e895906540a24ec627351d7ecaf47893774855dc5ad9051b"
}
toolread2.5.0No change observed
investigate_vmvmware-skills-vmware-aiops:tool:investigate_vm
Observed interface and hashes

[READ] "What is happening around this VM?" — one correlated drill-down. Correlates everything around one VM so you don't stitch it together yourself: the VM's state, its host, cluster context, backing datastores, snapshots, triggered alarms, live performance, and a merged **event timeline** across VM, host, cluster and datastores (newest first). Batched, cheap even on large fleets. Delegates to the vmware-monitor library (read-only). Explain the result in operational language; do not dump it raw. Use this AFTER get_cluster_health_summary points at a problem VM. Point-in-time.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "hours": {
      "default": 24,
      "description": "Event-timeline look-back window in hours (default 24).",
      "title": "Hours",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config (default if omitted).",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact VM name. Unknown names return a teaching error (list VMs first).",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "investigate_vmArguments",
  "type": "object"
}
sha256:1b46cf4a3dab2cdd67d411f845c137f2a80f58dc282a5d3a7bb202aa1462fc7a

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7f092051722ed3feca098165ae7bc940915346d5968f2a55a48b895a64915e12

Interface hash: sha256:cbe68052ef46eafd5af4ecce82a47a5bb91e9af0f862246786655b2ab6f09333

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/investigate_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "investigate_vm"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:61178cb8a23d7a8001eaf68c3d8a93c5f378de4f059a4207cd51dd9406f5426c"
}
toolread2.5.0No change observed
list_drs_rulesvmware-skills-vmware-aiops:tool:list_drs_rules
Observed interface and hashes

[READ] List a cluster's DRS rules: VM-VM affinity/anti-affinity and VM-Host. Per rule: key, name, type (affinity / antiAffinity / vmHost), enabled, mandatory, and the member VM names (VM-VM) or group names (VM-Host). The verify pair for create/delete/set_drs_rule_enabled. Returns: Dict with cluster, count, and rules sorted by name. Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster": {
      "description": "Exact cluster name.",
      "title": "Cluster",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "cluster"
  ],
  "title": "list_drs_rulesArguments",
  "type": "object"
}
sha256:b103da16ebd611c511ee2b728bfe8929e30e3df7ab0a07ba86d29160e43efece

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ac70463a0021e6e62656807c510168bc4bdb14bfa5a4097e7c3b34049d82623b

Interface hash: sha256:348b13666117b41e728a84a000b17fadd9ab5af6583698a5a54a947254034f9c

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_drs_rules",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_drs_rules"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:354e4326a7269ee5b4d3a764dc6bcf0cfa76c38ac76e4a80d40731cbce151255"
}
toolread2.5.0No change observed
list_dvs_portgroupsvmware-skills-vmware-aiops:tool:list_dvs_portgroups
Observed interface and hashes

[READ] List distributed virtual portgroups, optionally scoped to one dvSwitch. Per portgroup: name, parent dvSwitch, binding type (earlyBinding / ephemeral), VLAN setting (id, trunk ranges, or pvlan), configured port count, and whether it is the switch's uplink portgroup. Use to verify create_dvs_portgroup results or to survey network config before changes. Returns: The family list envelope {items, returned, limit, total, truncated, hint}; each item is one portgroup. `portgroups` is kept as a deprecated alias for `items`. Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "dvs_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "dvSwitch name to scope to; omit to list across all switches.",
      "title": "Dvs Name"
    },
    "limit": {
      "default": 200,
      "description": "Max portgroups to return (default 200).",
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "description": "Skip this many portgroups first (paging).",
      "title": "Offset",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "title": "list_dvs_portgroupsArguments",
  "type": "object"
}
sha256:0f6358ec47597878a52ee83c1e4d2633a78c7fc4841c56a080c2eaf031d79573

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5fe36c18dbb15d0b0344ee1f61198b25b10aa97bfe63df93242ce71d97d5213c

Interface hash: sha256:4fc3777df1517deb6e563a2d3fcb513c4a72418e83e4e6c6a1ca770e92485277

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_dvs_portgroups",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_dvs_portgroups"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:6b7cd3e1edc29cd9d7ab74e99a926d755043ab8ad76d687e046472e34c26c23e"
}
toolread2.5.0No change observed
list_host_vmksvmware-skills-vmware-aiops:tool:list_host_vmks
Observed interface and hashes

[READ] List VMkernel adapters, optionally scoped to one ESXi host. Per vmk: device, IP/netmask/dhcp, MTU, MAC, portgroup (standard or DVS), netstack, and which host services it is selected for (management, vmotion, vsan, ...). The verify pair for add_host_vmk/remove_host_vmk. Gotcha - this list is not automatically a complete estate inventory. vCenter answers property reads for a host it has lost contact with out of its own cache, so hosts it never reached appear here as rows with `reachable: false`, `device: null` and a `note` naming the connectionState, rather than being dropped. Check `hosts_unreachable` (and the `unreachable_note` present only when it is non-zero) before reporting the result as the full picture, and do not read a null field on such a row as a measurement - it means nobody looked. Adapters shown for an unreachable host are vCenter's last cached view. Returns: The family list envelope {items, returned, limit, total, truncated, hint} plus `hosts_unreachable` (int) and, when that is non-zero, `unreachable_note` (str). Each item is one VMkernel adapter, or one unread host when `reachable` is false; `services` is null when a host's service map could not be read. `truncated` stays a paging fact - an incomplete estate is reported by `hosts_unreachable`, not by it. `vmks` is kept as a deprecated alias for `items`. Errors return "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "host_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "ESXi host name; omit to list across all hosts.",
      "title": "Host Name"
    },
    "limit": {
      "default": 100,
      "description": "Max vmks to return (default 100).",
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "description": "Skip this many vmks first (paging).",
      "title": "Offset",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "title": "list_host_vmksArguments",
  "type": "object"
}
sha256:6c9eafcfbe0cd2c99981e1aada074b1263b33f1bf0c4d472b87911e2e42eb9c7

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7bf70efd3dc9d3bf6497b349d227808558120f65fa76a48717d2caf69d46effd

Interface hash: sha256:62fa317e7b2b2e9224197aa1747654cd59160d86e39a97838ca198e3e08151a7

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_host_vmks",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_host_vmks"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f04b7a99c72cb7a46b29b79f9c38b4cfe4de4d3e6a656a6b6051924ef4806793"
}
toolread2.5.0No change observed
list_vcenter_alarmsvmware-skills-vmware-aiops:tool:list_vcenter_alarms
Observed interface and hashes

[READ] List active/triggered alarms across the vCenter inventory. Start here for alarm work: it supplies the exact entity_name/alarm_name pair that acknowledge_vcenter_alarm and reset_vcenter_alarm require. Returns the list envelope: 'items' holds severity (critical/warning/info), entity name and type, alarm name, acknowledged flag, and trigger time; 'returned'/'limit'/'total'/'truncated'/'hint' state completeness, so a limited page is never mistaken for the whole picture. 'total' is the real active-alarm count — every alarm is collected before the limit is applied.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Max number of alarms to return (None = all). Use when many alarms are active.",
      "title": "Limit"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter target name from config. Uses default if omitted.",
      "title": "Target"
    }
  },
  "title": "list_vcenter_alarmsArguments",
  "type": "object"
}
sha256:9a48ee5f1aede344318f09cdf6b18d231ebcf1f34ecff7f1280e71d99cb140ba

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3da67fc2a4f43d578542d26f7082a86a210e2ff1e5ddacc601deca9d02725f30

Interface hash: sha256:2ac7660872d499fcb1c33166cf7c24a21e5a42ad35fc36067dff04cc0ef9087f

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_vcenter_alarms",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_vcenter_alarms"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:996524a04a89c6b2a327ade11e1edb3cf9dec01dc7a6e2cc663dc3a96d524a61"
}
toolread2.5.0No change observed
list_vm_plansvmware-skills-vmware-aiops:tool:list_vm_plans
Observed interface and hashes

[READ] List all pending/failed plans. Use this first to find a plan_id for apply_vm_plan or rollback_vm_plan. Returns the list envelope: 'items' holds plan summaries (plan_id, created_at, status, steps count, VMs affected), and 'returned'/'total'/ 'truncated' state whether the listing is complete. Every plan file is read, so truncated is always false. Listing never deletes: stale plans (>24h) are swept by create_vm_plan, not by this tool.

Input schema

{
  "additionalProperties": false,
  "properties": {},
  "title": "list_vm_plansArguments",
  "type": "object"
}
sha256:ae9e3cd1eef6c06858028d9e92687f9f870a05da7bf98637f12007fb6357ca87

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b090f15f5cf69ebc824a80132e5a8cfd656a697b8101783577f02136301d5d3a

Interface hash: sha256:2a57c984cc0e61a74563000dbbd813a0d29dbc7c8157b6333a79ba59bade6f6c

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_vm_plans",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_vm_plans"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:3f95a41cb1498411a6275f55792b1ba05b610965de980f7f23691e178e92547e"
}
toolread2.5.0No change observed
list_vm_snapshotsvmware-skills-vmware-aiops:tool:list_vm_snapshots
Observed interface and hashes

[READ] List the full snapshot tree of a VM, including nested child snapshots. Read-only, no side effects. Call this before revert_vm_snapshot, delete_vm_snapshot, or deploy_linked_clone to get exact snapshot names. 'items' is empty when the VM has no snapshots. Returns: The list envelope. 'items' is one dict per snapshot: name, description, created, state (power state at snapshot time), level (0 = root). The whole tree is walked, so 'total' is the real count and 'truncated' is always false.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact VM name as shown in vCenter inventory.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "list_vm_snapshotsArguments",
  "type": "object"
}
sha256:f8a31c643c0c78c42122d4460cf675566915953e375caea3cae891c3e47b502c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7ac459da33f4d3ff86835ca48b8c1cd517edd637b5406502f471d04f3355d66f

Interface hash: sha256:ef7d4fe1121d5dc3f7ab7b4c9c45aa18d7f72de2d1d1afd261babb180088c833

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_vm_snapshots",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_vm_snapshots"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:d825265f21b84fe711a83a31c9fa8f810f13a538ef292d3932eaebab19f1c3b8"
}
toolread2.5.0No change observed
list_vm_ttlsvmware-skills-vmware-aiops:tool:list_vm_ttls
Observed interface and hashes

[READ] List all VMs with TTLs registered, including expiry time and status. Use this first to find the exact vm_name for cancel_vm_ttl. Returns the list envelope: 'items' holds TTL entries with remaining_minutes and expired flag, and 'returned'/'total'/'truncated' state whether the listing is complete. The whole TTL store is read, so truncated is always false.

Input schema

{
  "additionalProperties": false,
  "properties": {},
  "title": "list_vm_ttlsArguments",
  "type": "object"
}
sha256:0db2bc2234bce8c1493693065949d0accb66f853790b7a438590fe1d164041f3

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c57711b37d98553e28a75dc1762b405dc4aba0d810413cae78f0937a7753243a

Interface hash: sha256:88e717264d451ef39c8c3d9a5833a152250d39746082ce57afdc6f3e3e318b0e

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/list_vm_ttls",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "list_vm_ttls"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:91a96347e3f126e679c7c435ec9ecd75d0ed941777036cfdd1e1899916046b1c"
}
toolread2.5.0No change observed
migrate_vmvmware-skills-vmware-aiops:tool:migrate_vm
Observed interface and hashes

[WRITE] Migrate (vMotion) a VM to another host, optionally with storage vMotion. Without confirm=True this only previews: it returns blast_radius (VM and instance UUID, source host and datastores, target host with its connection and maintenance state, target datastore, and live vMotion vs cold migration) and moves nothing. Show it to the user and get their decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused: a target host that is not found, not connected, in maintenance mode or has no resource pool; a target datastore that is not found; a target host that does not mount the VM's datastores when to_datastore is omitted (vCenter rejects cross-host vMotion without shared storage — pass to_datastore); and anything above that cannot be read. The VM's current host with no to_datastore returns action "noop". Run get_cluster_info first for host names. Returns: Dict with action (preview, noop, migrated), blast_radius, and result.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "to_datastore": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Target datastore (required for cross-storage hosts).",
      "title": "To Datastore"
    },
    "to_host": {
      "description": "Target ESXi host name.",
      "title": "To Host",
      "type": "string"
    },
    "vm_name": {
      "description": "VM to migrate.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "to_host"
  ],
  "title": "migrate_vmArguments",
  "type": "object"
}
sha256:001e133119c9f17f85c8a10939c308b310ba8c51fedc56bc5248b82f42f7bf13

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:754f4d7618a5a96fa3247ef6143f88e5168797c7078c1672c122acb247b75a0d

Interface hash: sha256:18821170cfa961436d27b96c0a8626514eac67066070220513c673a97a36db1d

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/migrate_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "migrate_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:3a7d599d09da3837bf03f28a7568865d8dfa87a82ff991aff2b8dc59b5934d55"
}
toolwrite2.5.0No change observed
ping_from_vmkvmware-skills-vmware-aiops:tool:ping_from_vmk
Observed interface and hashes

[READ] DF-bit-capable ping sourced from a host vmk - MTU path validation. Runs `esxcli network diag ping` on the ESXi host through the vSphere API (no host SSH). df=True sets Don't-Fragment so an oversized packet FAILS instead of fragmenting - that failure is the diagnostic: - df=True size=1572 proves a >=1600 MTU path (overlay/TEP floor) - df=True size=8972 proves full jumbo (9000 minus 28 bytes overhead) A too-big result reports 'Message too long' in the fault field rather than erroring - read success + fault together. Returns: Dict with request, success, and summary (transmitted/received/loss/ rtt) or fault (the esxcli failure text). Errors return "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "count": {
      "default": 3,
      "description": "Packets to send (default 3, max 60).",
      "title": "Count",
      "type": "integer"
    },
    "dest_ip": {
      "description": "IPv4 address to ping.",
      "title": "Dest Ip",
      "type": "string"
    },
    "df": {
      "default": false,
      "description": "True sets the Don't-Fragment bit (the MTU probe mode).",
      "title": "Df",
      "type": "boolean"
    },
    "host_name": {
      "description": "ESXi host to source the ping from.",
      "title": "Host Name",
      "type": "string"
    },
    "netstack": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional netstack instance (e.g. \"vxlan\" for real TEP vmks).",
      "title": "Netstack"
    },
    "size": {
      "default": 56,
      "description": "ICMP payload bytes (default 56). Path proves size+28 MTU.",
      "title": "Size",
      "type": "integer"
    },
    "source_vmk": {
      "description": "VMkernel device to source from (e.g. \"vmk2\").",
      "title": "Source Vmk",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "host_name",
    "source_vmk",
    "dest_ip"
  ],
  "title": "ping_from_vmkArguments",
  "type": "object"
}
sha256:c885758b6080cbe1c864be0a68ad6f645b74bd4c11ec6b3a60049e7afd9e94e6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:35d3aa1f60c14f4adc88fe71fb95305d5e23c95e5067765496f32ad0300072b4

Interface hash: sha256:9da710c16a20f53f7df98bde9ab49141d71ee631e9b5342c64e52c11b5f97ac8

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/ping_from_vmk",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "ping_from_vmk"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8031aa971faf856e71cc2ea8e6546c9716c23b3d905a77f710c0235ce925cc77"
}
toolread2.5.0No change observed
power_off_vmvmware-skills-vmware-aiops:tool:power_off_vm
Observed interface and hashes

[WRITE] Power off a VM — graceful guest shutdown by default, hard power-off with force=True. Without confirm=True this only previews: it returns blast_radius (VM name and instance UUID, host, power state, VMware Tools status, and whether this is a guest shutdown or a hard power-off) and changes nothing. Show it to the user and get their decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Graceful mode calls VMware Tools guest shutdown and waits up to 120s; if it does not finish, action is "still_running". Refused: a graceful shutdown when Tools is not running or the VM is suspended (preview force=True instead), and a VM whose identity or power state cannot be read. An already-off VM returns action "noop". Use power_on_vm to start a VM; delete_vm requires it off first. Returns: Dict with action (preview, noop, powered_off, still_running), blast_radius, and the executor's message under result.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "force": {
      "default": false,
      "description": "False (default) = graceful guest shutdown via VMware Tools; True = immediate hard power-off (risks guest filesystem damage).",
      "title": "Force",
      "type": "boolean"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target from config.yaml; omit for the default target.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact VM name as shown in vCenter inventory (case-sensitive).",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "power_off_vmArguments",
  "type": "object"
}
sha256:acc8aeabb84c2f738c81dfa58cb9ba8a397142f0474ed0b4191787a0c9fe3e90

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:317e5526985035c79ea6d238e98304c70897a72605e5a6e6641f28e712b7e302

Interface hash: sha256:3d40a1a5f0c90d582be131759977cbc10b9e48999f2a5f9362a2ebd909e34c18

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/power_off_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "power_off_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a8d71ecfb1bbf99bfeb1faf5a164e6381c29283912de28fbd2e1bad56bbbe0b9"
}
tooldestructive2.5.0No change observed
power_on_vmvmware-skills-vmware-aiops:tool:power_on_vm
Observed interface and hashes

[WRITE] Power on a virtual machine. Returns a status string; an already-on VM is a no-op. Reverse with power_off_vm. Call this first when a VM is off: guest tools such as run_vm_guest_command only work once VMware Tools has finished booting.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config. Uses default if omitted.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact name of the virtual machine.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "power_on_vmArguments",
  "type": "object"
}
sha256:3dbb82b735245f53a8df9859f2b8efcdf326bc87adb41b7f85507e48fe3b7aa4

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "power_on_vmOutput",
  "type": "object"
}
sha256:d76d49e042bf903c084f8296f6bea15888992ea338af73f9edc095edb37bfedf

Description hash: sha256:f7ac76cd67359cd1c3cffeb2cd75815df76cce408c642e4fd69bb2456f658fac

Interface hash: sha256:b55d23217d61cb323d7e018448c01d757bb10a9304fcf0e671a838e091e5fc93

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/power_on_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "power_on_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5b25a792531dcc52262e859aed23a4372101d27c5f5a04c9ec1baf0638252227"
}
toolwrite2.5.0No change observed
provision_vm_guestvmware-skills-vmware-aiops:tool:provision_vm_guest
Observed interface and hashes

[WRITE] Provision a VM by running an ordered sequence of guest operations. Prefer this over repeated run_vm_guest_command / upload_vm_guest_file calls when the steps form one provisioning run. Steps stop on the first failure, so a partial run leaves the guest half-configured. Requires VMware Tools running in the guest. Without confirm=True this only previews: blast_radius names the VM (name, instance UUID), the guest account and every step it would run, in order, with counts per type, local file sizes and any blockers; nothing runs. Show it to the user. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused outright: VM not powered on, VMware Tools not running, an empty step list, a step with an unknown type or a missing key, an upload whose local file is missing or unreadable, a service step on a Windows guest, an unreadable identity or status, a name that matches more than one VM, or a rules.yaml deny on a guest tool these steps run: exec and service steps run_vm_guest_command and run_vm_guest_command_with_output, upload steps upload_vm_guest_file (the preview lists it as a blocker). Step types: - exec: {"type": "exec", "command": "apt-get install -y nginx"} - upload: {"type": "upload", "local_path": "...", "guest_path": "..."} - service: {"type": "service", "name": "nginx", "action": "start"} Returns: dict with success, completed_steps, total_steps, results, error, and blast_radius.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "password": {
      "description": "Guest OS password.",
      "title": "Password",
      "type": "string"
    },
    "steps": {
      "description": "Ordered list of step dicts (see Step types).",
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Steps",
      "type": "array"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "timeout": {
      "default": 300,
      "description": "Per-step timeout in seconds (default 300).",
      "title": "Timeout",
      "type": "integer"
    },
    "username": {
      "description": "Guest OS username.",
      "title": "Username",
      "type": "string"
    },
    "vm_name": {
      "description": "Target VM name.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "username",
    "password",
    "steps"
  ],
  "title": "provision_vm_guestArguments",
  "type": "object"
}
sha256:04d28e8f4e60578da99577ad899299c9b430f3b0d6c4b861df1770ca9d9aab5c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:972c1b951d2c421f461ff151794caaae9e9e1488b70a40ba7af386bf97739a57

Interface hash: sha256:e87836d4b549f34be50ce6d999610399d96d584b13973f3a280f944000e27d9f

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/provision_vm_guest",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "provision_vm_guest"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:d03618a45bc619d1fcfd5aed834aa25f9a53a6152ca483ed609ef5f692c1a3bb"
}
tooldestructive2.5.0No change observed
reconfigure_vmvmware-skills-vmware-aiops:tool:reconfigure_vm
Observed interface and hashes

[WRITE] Change a VM's vCPU count and/or memory. Pass only the fields you want to change; omitted fields are left untouched. Hot-add of CPU/memory requires it to be enabled on the VM and a running guest; otherwise power the VM off first (power_off_vm). Returns: Status string describing the applied change, or a VM-not-found error.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cpu": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "New vCPU count; omit to leave unchanged.",
      "title": "Cpu"
    },
    "memory_mb": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "New memory in MB; omit to leave unchanged.",
      "title": "Memory Mb"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Exact name of the VM to reconfigure.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "reconfigure_vmArguments",
  "type": "object"
}
sha256:e22b9dd5bcb439c25c51fdf2d4ad49f2100fb31ebf9da047b96dd9cf4cf3b2c1

Output schema

{
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "reconfigure_vmOutput",
  "type": "object"
}
sha256:da83f5e0d59fdf4b285918ac6492b7890fa0abcd9483f3acbd6848f3073503f9

Description hash: sha256:0d0155521d192cfb9c58317af1742d5e02af0949d03abe7a9085196eab89683a

Interface hash: sha256:02f1dc7b3d5efdf4a469d42662722208442046e16a0c531f188be94128fc2cd0

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/reconfigure_vm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "reconfigure_vm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:807f2c8a73db7758aeb977aff9382490be7bc6bd676dd72dd7ee0e9eb8ea7878"
}
toolwrite2.5.0No change observed
remove_cluster_hostvmware-skills-vmware-aiops:tool:remove_cluster_host
Observed interface and hashes

[WRITE] Remove a host from a cluster (host must be in maintenance mode). Without confirm=True this only previews: it returns blast_radius (host name and id, maintenance mode, VM count, powered-on VM count, blockers) and moves nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused: a host not in maintenance mode, a host with powered-on VMs, and a host whose state could not be read. Run get_cluster_info first for the exact member host names. The host is not deleted — it stays in vCenter inventory standalone; use add_cluster_host to move it back. Returns a dict.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster_name": {
      "description": "Cluster to remove the host from.",
      "title": "Cluster Name",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "host_name": {
      "description": "ESXi host name to remove (from get_cluster_info output).",
      "title": "Host Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter target name from config.",
      "title": "Target"
    }
  },
  "required": [
    "cluster_name",
    "host_name"
  ],
  "title": "remove_cluster_hostArguments",
  "type": "object"
}
sha256:d4828d5c59a4cf45f9a6d093718252cc3e60f5c6b47f38f218a71e730cfc0778

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:73f60080e0d3172439fdb602289b59ee016f8eced759257d29b7d645fc89ba89

Interface hash: sha256:46699e5a3572e9495694c2563ec60061e1d97cf7e1fc1b8cb3e0789cb107d476

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/remove_cluster_host",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "remove_cluster_host"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0f4687ce8914e76813ebe53e4da5e680c8ec69da4056a599ce6ee4f7032b19f4"
}
tooldestructive2.5.0No change observed
remove_host_vmkvmware-skills-vmware-aiops:tool:remove_host_vmk
Observed interface and hashes

[WRITE] Remove a VMkernel adapter - confirm-gated, guarded, fail-closed. REFUSES (unless force_unprotected=True) when the vmk is selected for any host service (management/vmotion/vsan/...), lives on a non-default netstack (NSX TEPs on vxlan, dedicated vmotion/provisioning stacks - never visible in the service map), carries a default gateway route, or when any of that CANNOT be verified - unverifiable is treated as unsafe, never as clear. Test vmks created by add_host_vmk trip none of these and remove cleanly without force. ABSOLUTE, no override: the host's only management-enabled vmk is never removable - this call rides the interface it would delete. force_unprotected=True (together with confirm=True) overrides the non-absolute protections for deliberate teardown; the override and every bypassed protection are recorded in the result (and the audit trail). Returns: Preview dict (action="preview") or result dict (action="removed", plus forced/protections_bypassed when overridden). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True removes it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "force_unprotected": {
      "default": false,
      "description": "True bypasses the non-absolute protections above.",
      "title": "Force Unprotected",
      "type": "boolean"
    },
    "host_name": {
      "description": "ESXi host the vmk lives on.",
      "title": "Host Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "vmk": {
      "description": "Device name to remove (e.g. \"vmk2\").",
      "title": "Vmk",
      "type": "string"
    }
  },
  "required": [
    "host_name",
    "vmk"
  ],
  "title": "remove_host_vmkArguments",
  "type": "object"
}
sha256:f9d642b9b493c13f9911899f4e0117b9e5d6a37ad9c22698d5e45d2e50a6921b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:a33b22286da33867eb3c81b144fa774533d0262a14d7bc1bb5545852cd98fd23

Interface hash: sha256:5cf19d73b57fab61553319a9961ee5398edfe17bbbded433241fe1175ead5467

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/remove_host_vmk",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "remove_host_vmk"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:14c98ff602ab0c4d9abcc82e3a6381d6876822f9d60743e5bfa34a9cb19f03b5"
}
tooldestructive2.5.0No change observed
reset_vcenter_alarmvmware-skills-vmware-aiops:tool:reset_vcenter_alarm
Observed interface and hashes

[WRITE] Clear triggered vCenter alarms back to normal state. Use this after resolving the underlying issue; to merely mark an alarm seen use acknowledge_vcenter_alarm instead. Get entity_name and alarm_name from list_vcenter_alarms first. vSphere has no per-alarm clear: this clears EVERY triggered alarm with the named alarm's status (red/yellow) on its entity type (host/VM/all), usually more than the one named. Without confirm=True this only previews: it returns blast_radius with will_clear_count and the alarms it would clear, and changes nothing. Show it to the user and get their decision; do not set confirm=True on your own. Refused when the list of alarms cannot be read. Returns: Dict with action (preview, reset), blast_radius, and on reset the scope cleared.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "alarm_name": {
      "description": "Exact alarm definition name from list_vcenter_alarms output.",
      "title": "Alarm Name",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True clears.",
      "title": "Confirm",
      "type": "boolean"
    },
    "entity_name": {
      "description": "Name of the entity with the alarm (VM name, host name, or cluster name).",
      "title": "Entity Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter target name from config.",
      "title": "Target"
    }
  },
  "required": [
    "entity_name",
    "alarm_name"
  ],
  "title": "reset_vcenter_alarmArguments",
  "type": "object"
}
sha256:3dbfd5c2beddeebd7ac18b9221f535845c2fe30b73f2f0ce659f0c0eff00a18c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b058c03e8d81d64eee5ea7b580ff99e2bb63aad12ba13ef809ef030f43e157c4

Interface hash: sha256:7bf583b09c274bbeb72a9d385cf07a2e61843d64583978f92a944013d841c1dd

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/reset_vcenter_alarm",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "reset_vcenter_alarm"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2dd0642a203e22f84af7c8605074bf4dd8a115aa0d8be470ee63fd12af7d057a"
}
tooldestructive2.5.0No change observed
restore_vm_clean_slatevmware-skills-vmware-aiops:tool:restore_vm_clean_slate
Observed interface and hashes

[WRITE] Revert a VM to its baseline snapshot (Clean Slate). Without confirm=True this only previews: it returns blast_radius (VM identity, power state and whether it is powered off first, the snapshot and when it was taken, snapshot count, blockers) and changes nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. With confirm=True: powers off the VM first if it is running, then reverts to the named snapshot. Use this to reset a lab/dev VM to a clean starting state after a task completes. Irreversible — everything written since the snapshot is lost. Refused: no snapshot of that name, more than one, a VM whose state cannot be read, or a rules.yaml deny on power_off_vm or revert_vm_snapshot (the preview lists it as a blocker). Returns a dict (action, blast_radius).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "snapshot_name": {
      "default": "baseline",
      "description": "Snapshot name to revert to (default: \"baseline\").",
      "title": "Snapshot Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Name of the VM to revert.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name"
  ],
  "title": "restore_vm_clean_slateArguments",
  "type": "object"
}
sha256:f8747035a97f0d97cfdf91e9743ee35185031d3b9f843aa241f7f703178b7aff

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:d13adf61dc522939b4d79f59253aa70a6f7affec6a8a378e30fde6525d576a2f

Interface hash: sha256:6713648d7b34da53e651edd09c6e00751298d0cc273efa95abb5caa756f44239

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/restore_vm_clean_slate",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "restore_vm_clean_slate"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:ed7fb4cb35393362de0038093b9231e9c33d4b57f4f3badb15bdfed831f6a851"
}
tooldestructive2.5.0No change observed
revert_vm_snapshotvmware-skills-vmware-aiops:tool:revert_vm_snapshot
Observed interface and hashes

[WRITE] Revert a VM to a named snapshot (loses changes since snapshot). Without confirm=True this only previews: it returns blast_radius (VM and instance UUID, the snapshot's name, id and creation time, total snapshot count, current power state and the power state after the revert) and changes nothing. Show it to the user and get their decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Irreversible — everything written since the snapshot is lost. Refused: a snapshot name that is not found, a name that matches more than one snapshot on the VM (vSphere allows duplicates; rename one first), and a VM whose snapshot tree, identity or power state cannot be read. Run list_vm_snapshots first for exact names. To reclaim space without changing state use delete_vm_snapshot. Returns: Dict with action (preview, reverted), blast_radius, and result.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "snapshot_name": {
      "description": "Snapshot to revert to.",
      "title": "Snapshot Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_name": {
      "description": "VM to revert.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "snapshot_name"
  ],
  "title": "revert_vm_snapshotArguments",
  "type": "object"
}
sha256:61570c4427078699b60933fae91f87e13d2f7008ee06978c4e5f8b8c24769c8f

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:4eb78641b0b7aa15a6ec357f57b08ec4b5a12d820aa5eb1d06dec6b7f313d299

Interface hash: sha256:3fb1741ad710e6670f45e51d760bff2d8ca8315a3f2d13155e33ba5fff45922a

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/revert_vm_snapshot",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "revert_vm_snapshot"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:167e4047845d6205f5bd7cb1b82a4094cf75bb64fbff608d97ac8fd8bf945942"
}
tooldestructive2.5.0No change observed
rollback_vm_planvmware-skills-vmware-aiops:tool:rollback_vm_plan
Observed interface and hashes

[WRITE] Rollback executed steps of a failed plan in reverse order. Without confirm=True this only previews: it returns blast_radius listing the rollback steps that would run (in order, with the VMs a rollback deletes) and those skipped as irreversible — and runs nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Only call this after apply_vm_plan returns status='failed'; check list_vm_plans first for the plan_id. Irreversible steps (delete_vm, revert_snapshot, etc.) are skipped with a warning. Each destructive rollback step (power off, delete snapshot, cluster delete, host removal) is measured as its own tool measures it, in the preview and again just before it runs; a refused check stops the rollback there and the plan stays 'failed'. Refused on a target other than the one the plan was created against, and for any rollback step ~/.vmware/rules.yaml denies for its own tool (deleting a VM the plan created is authorized as delete_vm).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "plan_id": {
      "description": "The plan ID of the failed plan.",
      "title": "Plan Id",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The vCenter/ESXi target the plan was created against.",
      "title": "Target"
    }
  },
  "required": [
    "plan_id"
  ],
  "title": "rollback_vm_planArguments",
  "type": "object"
}
sha256:59cdd9ae483ccff2367c2c8213d64f30799c031521c9a13bd874ad48dc3de969

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c8157735ae2b259f34d2d8c642cffa3357a0b8b899fa1200aec605e82d27fbba

Interface hash: sha256:7880f281920da626839f62185bdf44a040948e174676d572ca6cfa0ba3e0eb6c

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/rollback_vm_plan",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "rollback_vm_plan"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2f4606c3f25c18a0d810346874982c18fb06f93fca4399d4d1aa83da074d6ea4"
}
tooldestructive2.5.0No change observed
run_vm_guest_commandvmware-skills-vmware-aiops:tool:run_vm_guest_command
Observed interface and hashes

[WRITE] Execute a command inside a VM via VMware Tools. Requires VMware Tools running in the guest OS. Returns exit_code, stdout, stderr, timed_out, and blast_radius. Without confirm=True this only previews: blast_radius names the VM (name, instance UUID), the guest account, the exact command, arguments and working directory, VMware Tools status and any blockers; nothing runs. Show it to the user. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused outright: VM not powered on, VMware Tools not running, an identity or status that cannot be read, or a name that matches more than one VM. Note: the Guest Ops API does not capture stdout/stderr directly, so use this only for fire-and-forget commands — prefer run_vm_guest_command_with_output whenever you need the output.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "arguments": {
      "default": "",
      "description": "Command arguments (e.g. \"-c 'whoami'\").",
      "title": "Arguments",
      "type": "string"
    },
    "command": {
      "description": "Full path to program (e.g. \"/bin/bash\", \"C:\\Windows\\System32\\cmd.exe\").",
      "title": "Command",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "password": {
      "default": "",
      "description": "Guest OS password.",
      "title": "Password",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "username": {
      "description": "Guest OS account to run as. Required — there is no default, so a call can never act as root without choosing root.",
      "title": "Username",
      "type": "string"
    },
    "vm_name": {
      "description": "Target VM name.",
      "title": "Vm Name",
      "type": "string"
    },
    "working_directory": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Working directory inside guest (optional).",
      "title": "Working Directory"
    }
  },
  "required": [
    "vm_name",
    "command",
    "username"
  ],
  "title": "run_vm_guest_commandArguments",
  "type": "object"
}
sha256:6d12e1a57030c66d19aa55681708bcaf643a70017158d7beb8fa6936c91abdab

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3e4068c7d678e9e8f4c3e9bac7138ce28c7d2c6f0ba19bda9d9762ac15a75be0

Interface hash: sha256:486bf0420cad0dfe06e7fd4e842b041ecd2dcfea64af141e19391a89d0e93298

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/run_vm_guest_command",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "run_vm_guest_command"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a48335862b99f9d52b2b3c7071db1cbc97cc0cc529dea38200a4bd201520ad97"
}
tooldestructive2.5.0No change observed
run_vm_guest_command_with_outputvmware-skills-vmware-aiops:tool:run_vm_guest_command_with_output
Observed interface and hashes

[WRITE] Execute a shell command inside a VM and capture stdout + stderr. Automatically detects guest OS (Linux/Windows) and selects the correct shell. Output is captured by redirecting to a temp file, downloading it, then cleaning up — no manual redirection needed. Prefer this over run_vm_guest_command whenever you need the output. Requires VMware Tools running and a writable temp directory in the guest. Returns exit_code, stdout, stderr, timed_out, os_family, and blast_radius. Without confirm=True this only previews: blast_radius names the VM (name, instance UUID), the guest account, the exact command and the shell it runs through, VMware Tools status and any blockers; nothing runs. Show it to the user. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused outright: VM not powered on, VMware Tools not running, an unreadable identity or status, a name that matches more than one VM, or a rules.yaml deny on run_vm_guest_command or download_vm_guest_file (the preview lists it as a blocker).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "command": {
      "description": "Shell command (e.g. \"df -h\", \"ls /etc\", \"ipconfig\").",
      "title": "Command",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "password": {
      "default": "",
      "description": "Guest OS password.",
      "title": "Password",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "timeout": {
      "default": 300,
      "description": "Max wait seconds (default 300).",
      "title": "Timeout",
      "type": "integer"
    },
    "username": {
      "description": "Guest OS account to run as. Required — there is no default, so a call can never act as root without choosing root.",
      "title": "Username",
      "type": "string"
    },
    "vm_name": {
      "description": "Target VM name.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "command",
    "username"
  ],
  "title": "run_vm_guest_command_with_outputArguments",
  "type": "object"
}
sha256:6035b75db8cee7c577c26948e6732538775aa4888c746fd2ac8e0e55216e5e96

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:29ae5555ef660122c170ac59e50f32a1c3866e7a906a50e0ce3a51922c97ba8c

Interface hash: sha256:8e6acb0b4d09d66ecb30ae087b71861c9e712cbc03312bd6c7c00d46294beb33

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/run_vm_guest_command_with_output",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "run_vm_guest_command_with_output"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5b2932f006f549574d50baf9cd7d78f53a3d3916e2320c8ae16807bfa2a74aa3"
}
tooldestructive2.5.0No change observed
scan_all_datastore_imagesvmware-skills-vmware-aiops:tool:scan_all_datastore_images
Observed interface and hashes

[READ] Scan all accessible datastores for deployable images (OVA/ISO/OVF/VMDK). Returns the images found and refreshes the cache at ~/.vmware-aiops/image_registry.json. Use this when you do not know which datastore holds an image; prefer browse_datastore once you do, because this walks every datastore and may take minutes on a large estate. Returns: The family list envelope {items, returned, limit, total, truncated, hint} plus `last_scan`; each item is one image. `images` is kept as a deprecated alias for `items`.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    }
  },
  "title": "scan_all_datastore_imagesArguments",
  "type": "object"
}
sha256:bed385e1a894137a7bc410158e118d46beacb5e04fd2cb286977e14137d25a2d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:378b7d217cd73f4b43c587d67cbd87aaa36333d458522f4acad446f8977b2d26

Interface hash: sha256:18d838b2127fcd4e9564f06f6e3b3f4f97284c975577ecc4d3f1b2bbe7f68e3d

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/scan_all_datastore_images",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "scan_all_datastore_images"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5ac94e752dc840a883047b14b51612f87d82f31df6bc3be8c43fabe2b5c817be"
}
toolread2.5.0No change observed
set_drs_rule_enabledvmware-skills-vmware-aiops:tool:set_drs_rule_enabled
Observed interface and hashes

[WRITE] Enable or disable an existing DRS rule - preview/confirm gated. The day-2 toggle: anti-affinity rules often must be disabled while a cluster is temporarily too small to satisfy them, then re-enabled when hosts return. Idempotent - matching state returns a noop, no write. Names are matched exactly; ambiguous names refuse. Audited. Returns: Preview dict (action="preview"), noop dict (action="noop"), or result dict (action="set", rule_now). Errors return "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "cluster": {
      "description": "Exact cluster name.",
      "title": "Cluster",
      "type": "string"
    },
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "enabled": {
      "description": "True enables the rule; False disables it.",
      "title": "Enabled",
      "type": "boolean"
    },
    "rule_name": {
      "description": "Exact rule name (see list_drs_rules).",
      "title": "Rule Name",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    }
  },
  "required": [
    "cluster",
    "rule_name",
    "enabled"
  ],
  "title": "set_drs_rule_enabledArguments",
  "type": "object"
}
sha256:739e479a59e8014efee348f760530d421602b28b27b82a8289b7d49a942526c5

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3a7077c17d963c285d5578b2f54c1c4c096c26d54a95e86f1521ee65124efa1e

Interface hash: sha256:befc8034b64c11ed4839cb4d70ebc0ae68a0a892217ad79d73fff82e7c4682d1

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/set_drs_rule_enabled",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "set_drs_rule_enabled"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:ecaaf665d7bcb0f19997eca5b674f879973c05bc78193e9089776cafe3b23cc2"
}
toolwrite2.5.0No change observed
set_vm_ttlvmware-skills-vmware-aiops:tool:set_vm_ttl
Observed interface and hashes

[WRITE] Set a Time-To-Live (TTL) for a VM. The daemon auto-deletes it when expired. Without confirm=True this only previews: it returns blast_radius — the VM that will be deleted (identity, host, disks, total size, snapshot count), when (expires_at), and any TTL it replaces — and schedules nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused when the VM's identity or disks cannot be read. Use this for short-lived lab VMs so cleanup is not forgotten; cancel with cancel_vm_ttl and review pending expiries with list_vm_ttls. The scheduler daemon must be running (`vmware-aiops daemon start`) or nothing is ever deleted; it powers a running VM off first. TTLs persist in ~/.vmware-aiops/ttl.json. Returns a dict (action, blast_radius).

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "minutes": {
      "description": "Minutes until deletion (minimum 1).",
      "title": "Minutes",
      "type": "integer"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "vm_name": {
      "description": "Name of the VM to auto-delete.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "minutes"
  ],
  "title": "set_vm_ttlArguments",
  "type": "object"
}
sha256:ab14a14a90f78b2d3c2a0b8ec40b5124bc7a394b4f13f4e2826345d2b58c9e31

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c8d7d49407f2b426b9e06caaf4101c6c23c6af123f092902ce00bc07192ce265

Interface hash: sha256:89bb012bd3f0f59ef9217d66af932ed56777d95cef0091af436ca584521887de

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/set_vm_ttl",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "set_vm_ttl"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:3a4f26e6a86a353ce65fa9c2798f269f8948b4626d74d0f70d8c95f45da470c4"
}
tooldestructive2.5.0No change observed
set_vmk_servicevmware-skills-vmware-aiops:tool:set_vmk_service
Observed interface and hashes

[WRITE] Enable/disable a host service on an existing vmk - preview/confirm gated. Completes the add_host_vmk story: adapters are created serviceless by design, then tagged here (e.g. enable "vmotion" on a new vMotion vmk). Idempotent - re-applying the current state returns a no-write noop. Verify with list_host_vmks (the services field). Audited. Valid services are the vSphere nicType names: management, vmotion, vsan, vSphereProvisioning, faultToleranceLogging, vSphereReplication, vSphereReplicationNFC, vSphereBackupNFC, ptp, and the nvme/vsan variants. Note "vSphereProvisioning", not "provisioning". FAIL CLOSED: refuses both directions when the host's service map cannot be read. ABSOLUTE, no override: disabling management on the host's only management-enabled vmk - the call rides the interface it would untag. Returns: Preview dict (action="preview"), noop dict (action="noop") when the state already matches, or result dict (action="set", services_now). Errors return a dict with "error" + hint.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it. Do not set True because the user asked earlier; they have not seen the preview yet.",
      "title": "Confirm",
      "type": "boolean"
    },
    "enabled": {
      "description": "True selects the vmk for the service; False deselects.",
      "title": "Enabled",
      "type": "boolean"
    },
    "host_name": {
      "description": "ESXi host the vmk lives on.",
      "title": "Host Name",
      "type": "string"
    },
    "service": {
      "description": "Service/nicType name to enable or disable.",
      "title": "Service",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "vCenter target name from config.yaml; omit to use the default target.",
      "title": "Target"
    },
    "vmk": {
      "description": "Device name to change (e.g. \"vmk3\").",
      "title": "Vmk",
      "type": "string"
    }
  },
  "required": [
    "host_name",
    "vmk",
    "service",
    "enabled"
  ],
  "title": "set_vmk_serviceArguments",
  "type": "object"
}
sha256:814579bde7c790aa036bb4a8bee645772696650133a863cfdc083e68e9cc146c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:77447e7310c344883f88caf14ea6e294c2b554a9f4f6be1eef5a54a1bd0c8ba2

Interface hash: sha256:bf6d21a3356dfe261af5f227d6127b38b213d07e322164c7bdca4e60850cb2eb

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/set_vmk_service",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "set_vmk_service"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5f2d3efdbf8a895649448f2b5ebc13b3d588115b17fd228d9e5b6799d2551861"
}
toolwrite2.5.0No change observed
upload_vm_guest_filevmware-skills-vmware-aiops:tool:upload_vm_guest_file
Observed interface and hashes

[WRITE] Upload a file from local machine to a VM via VMware Tools. Returns a dict with action, message and blast_radius (a status string before the confirmation gate). Requires VMware Tools running in the guest OS. An existing file at guest_path is replaced. Use download_vm_guest_file for the reverse direction, and provision_vm_guest instead when uploads and commands belong to one ordered provisioning run. Without confirm=True this only previews: blast_radius names the VM (name, instance UUID), the guest account, the local path and size, the guest path, VMware Tools status and any blockers; nothing is transferred. Show it to the user. Do not set confirm=True on your own because the user asked earlier: they have not seen the preview yet. Refused outright: VM not powered on, VMware Tools not running, a local file that is missing or unreadable, an unreadable identity or status, or a name that matches more than one VM.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "confirm": {
      "default": false,
      "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      "title": "Confirm",
      "type": "boolean"
    },
    "guest_path": {
      "description": "Destination path inside the guest.",
      "title": "Guest Path",
      "type": "string"
    },
    "local_path": {
      "description": "Local file path to upload.",
      "title": "Local Path",
      "type": "string"
    },
    "password": {
      "default": "",
      "description": "Guest OS password.",
      "title": "Password",
      "type": "string"
    },
    "target": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional vCenter/ESXi target name from config.",
      "title": "Target"
    },
    "username": {
      "description": "Guest OS account to run as. Required — there is no default, so a call can never act as root without choosing root.",
      "title": "Username",
      "type": "string"
    },
    "vm_name": {
      "description": "Target VM name.",
      "title": "Vm Name",
      "type": "string"
    }
  },
  "required": [
    "vm_name",
    "local_path",
    "guest_path",
    "username"
  ],
  "title": "upload_vm_guest_fileArguments",
  "type": "object"
}
sha256:ec807c5e566281a68151819d298806bd605175605b6c8d0836c5ed43ee67f72e

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3c7cacd6ecc20a91ab74598a208f0476cc14ada567ff87f18b1ee49dfbf78425

Interface hash: sha256:e4e82b0d70df12d5d2d0aca1f7d510cc2a8261b82d4c167e38c2cca0add340e2

Other observed Modelara metadata
{
  "id": "mcp:vmware-aiops/upload_vm_guest_file",
  "source": {
    "type": "mcp",
    "server": "vmware-aiops",
    "operation": "upload_vm_guest_file"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5dcab8597b9013136d99f691c0cc04d9fc2d4e4056cd476bfe839333e0b7f61b"
}
tooldestructive2.5.0No change observed

STATIC COMPARISONS

Release history

2 release transitions
  1. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 17, 2026· Automated static analysis

  2. 0 added0 removed1 schema0 write0 destructive0 unknown

    Nov 17, 2026· Pending human review