Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VIBOPS_URLYesBase URL of your VibOps instance, e.g. https://vibops.example.com
VIBOPS_TOKENYesAPI token — create one in VibOps → Settings → API Tokens

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

You are connected to a VibOps instance that manages GPU Kubernetes infrastructure.

Routing guide:

  • Start with list_clusters to discover available clusters before taking any action.

  • list_clusters returns gateway_id per cluster — pass it to action tools when multiple gateways share a cluster name.

  • For general fleet health, call list_clusters then list_alerts then get_open_anomalies.

  • To investigate a specific cluster, call get_cluster_deployments.

  • GPU utilisation: get_gpu_metrics. Cost: get_cost_estimate. Workload types: get_workload_breakdown.

  • Job health (success rate, latency): get_job_metrics. For individual jobs: get_job or list_jobs.

  • To scale pods in a deployment, use scale_deployment. Do not use helm or run_kubectl for scaling.

  • To deploy a model, use deploy_model. For arbitrary Helm charts, use helm_upgrade.

  • Use run_kubectl only for operations not covered by dedicated tools (get, describe, logs).

  • Before triggering a pipeline, use list_pipelines to find its UUID.

  • GPU anomalies (idle, spike, node loss): get_open_anomalies, then resolve_anomaly once fixed.

  • Compliance controls (AI Act, GDPR, PDPL, HIPAA…): list_compliance_controls(framework=) + get_compliance_score(framework=). Update with update_compliance_control.

  • Compliance reports (SOC 2, RGPD, HIPAA): generate_compliance_report, then poll get_compliance_report.

  • Audit integrity: list_audit_logs to query events, verify_audit_chain to confirm no tampering.

  • Policy changes: get_policy first, modify, then update_policy. Changes are immediate.

  • Agent machine keys: list_agent_identities, create_agent_identity (key shown once), rotate_agent_identity, revoke_agent_identity.

  • Agent dependencies: get_agent_dependency_graph for org-wide view, get_agent_dependencies for one agent.

  • Job quality: list_eval_rubrics, evaluate_job, get_job_evaluations.

  • GPU cost & waste: get_budget, get_spend_trend, get_chargeback, get_waste_analysis.

  • LDAP / Active Directory: get_ldap_config to inspect, update_ldap_config to configure or enable/disable.

  • SIEM push: get_siem_config to inspect, update_siem_config to set Splunk/Datadog destination, push_to_siem to export audit events.

  • HPE VME (Morpheus): vme_list_instances, vme_get_instance, vme_list_servers, vme_list_clouds for inventory. vme_start/stop/restart_instance for lifecycle. vme_create_snapshot, vme_list_snapshots for protection. vme_convert_image for VMware→VME migration (vmdk→qcow2). vme_detect_vm_waste for FinOps.

  • Container registry: registry_list_repos, registry_list_tags, registry_check_image for inspection; registry_delete_tag (confirmed=True) to remove stale tags.

  • Agent inference FinOps: get_agent_usage for per-agent LLM cost attribution, get_agent_usage_detail for drill-down on a specific agent.

  • All write operations (deploy, scale, helm, kubectl, policy, identities) are recorded in the VibOps audit log.

  • VibOps jobs are infrastructure operations, not Kubernetes Jobs. Use list_jobs to review recent operations.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_clustersA

List all clusters registered in VibOps, with current GPU utilisation summary.

Start with this tool when the user asks about available clusters or general fleet status. For raw kubeconfig contexts (including clusters not yet registered in VibOps), use list_kubectl_contexts instead.

get_cluster_deploymentsA

Return live Kubernetes deployment status for a cluster, including replica counts, pod health, and resource usage. Polls the cluster via the VibOps gateway (up to 20s).

Call this when investigating deployment health, replica counts, or pod failures.

Args: cluster_name: Name of the cluster as returned by list_clusters. namespace: Restrict results to a single namespace (optional).

list_jobsA

List recent VibOps operations (scale, deploy, helm, kubectl...).

A VibOps job is not a Kubernetes Job — it represents any infrastructure operation submitted through VibOps. Use get_job to retrieve the full result of a specific operation.

Args: status: Filter by status — pending | running | success | failed. action: Filter by action type — scale_cluster | deploy_model | helm_upgrade | helm_uninstall | kubectl_exec | git_clone. limit: Maximum number of jobs to return (default 20, max 100).

get_jobA

Return the details and result of a specific VibOps operation.

Call this to check whether a previously submitted action succeeded or failed, and to retrieve its output (kubectl stdout, Helm output, error message).

Args: job_id: Full UUID or short ID (first 8 characters) of the job.

get_gpu_metricsA

Return hourly GPU utilisation time-series for the last N hours.

Use this to assess whether GPUs are idle, saturated, or trending toward failure. For cost implications of that utilisation, use get_cost_estimate. For a breakdown of what workloads are consuming the GPUs, use get_workload_breakdown.

Args: hours: Look-back window in hours (default 24, max 168).

get_workload_breakdownA

Return the distribution of GPU work by workload type for the last N hours. Types: inference | training | observation | operations | gitops | maintenance | other.

Use this to understand what your GPU fleet is being used for. For raw utilisation percentages, use get_gpu_metrics.

Args: hours: Look-back window in hours (default 24).

get_mttrA

Return Mean Time To Resolve (MTTR) for GPU alerts, broken down by cluster and severity.

Use this to assess operational reliability and incident response speed over time.

Args: hours: Look-back window in hours (default 168 = 7 days).

get_cost_estimateA

Return estimated GPU spend for the last N hours.

Requires cost rates to be configured per cluster (use set_cluster_rate). Returns null costs if no rates are configured. For GPU utilisation data without cost, use get_gpu_metrics.

Args: hours: Look-back window in hours (default 24).

get_job_metricsA

Return job execution SLIs for the last N hours: throughput, success rate, and p50/p95 latency broken down by action type.

Call this when the user asks whether operations are healthy, whether jobs are failing, or how long specific actions typically take. For individual job status, use get_job or list_jobs instead.

Response shape: summary.total — total jobs submitted summary.succeeded — jobs that completed successfully summary.failed — jobs that failed summary.in_flight — jobs currently pending or running summary.success_rate_pct — overall success rate (null if no jobs) by_action[].action — action name (scale_cluster, deploy_model, …) by_action[].p50_seconds — median execution time by_action[].p95_seconds — 95th-percentile execution time hourly[] — per-hour succeeded/failed counts for sparklines

Args: hours: Look-back window in hours (default 24, max 720).

get_vm_usageA

Get VM cost attribution across all hypervisors.

Returns per-VM cost estimate based on allocated vCPU, RAM, and disk. Includes hourly and monthly costs, sorted by most expensive first.

list_gatewaysA

List all registered VibOps gateways and their connection status.

A gateway is a remote agent installed in the customer infrastructure that bridges VibOps Core to local Kubernetes clusters and cloud APIs. To list clusters managed by those gateways, use list_clusters.

list_alertsA

List GPU infrastructure alerts (thermal throttling, OOM kills, low utilisation, hardware errors).

Call this when investigating performance degradation, unexpected restarts, or before making scaling decisions. Open alerts (resolved=False) indicate active issues.

Args: severity: Filter by severity — warning | critical. resolved: False for active alerts, True for resolved alerts. Omit for all.

list_secretsA

List secret names and metadata stored in the VibOps vault. Values are never returned.

Use this to check which credentials are available before submitting jobs that require them. To store a new secret, use create_secret.

Args: search: Filter by name (optional substring match).

list_providersA

List configured custom AI and GPU cloud providers (e.g. DGX Cloud, Scaleway, Outscale).

Providers extend VibOps with additional connectors beyond the built-in ones.

list_pipelinesA

List automation pipelines — named sequences of jobs that execute in order.

A pipeline is distinct from a single job: it orchestrates multiple operations (e.g. deploy to staging → health check → promote to production). To trigger a pipeline, use trigger_pipeline with its UUID.

Args: limit: Maximum number of pipelines to return (default 10, max 200).

get_cluster_rateA

Return the configured GPU cost rate for a cluster.

Used to verify the rate before interpreting get_cost_estimate results. To set or update the rate, use set_cluster_rate.

Args: cluster_name: Name of the cluster.

list_kubectl_contextsA

List raw kubectl contexts from the gateway's kubeconfig.

Use this only to discover clusters not yet registered in VibOps, or to debug context name mismatches. For normal cluster discovery, use list_clusters.

scale_deploymentA

Scale the replica count of a Kubernetes deployment.

Changes the number of running pods — does not add or remove cluster nodes. Set replicas to 0 to suspend a workload, 1 or more to run it.

Write operation — recorded in the audit log.

Args: cluster_name: Name of the target cluster (as returned by list_clusters). deployment_name: Name of the deployment to scale (e.g. llama3, ollama). replicas: Desired number of running pods (0 to suspend). namespace: Kubernetes namespace (default: 'default'). gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name.

deploy_modelA

Deploy an AI model onto a GPU cluster.

Use this for standard model deployments. For custom Helm chart deployments, use helm_upgrade instead.

Write operation — recorded in the audit log.

Args: cluster_name: Target cluster name. model_name: Model identifier (e.g. llama3:8b, mistral:7b). namespace: Kubernetes namespace (default: 'default'). replicas: Number of replicas (default 1). gpu_count: Number of GPUs to allocate per replica (optional). image: Override the default container image (optional). env: Environment variables to inject into the container (optional). gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name.

helm_upgradeA

Run helm upgrade --install for a chart on a cluster. Destructive — requires confirmed=True.

On an existing release this replaces the running workloads, so it is gated like any other destructive action: call once to get the dry-run preview, then again with confirmed=True.

Use this for Helm chart deployments. For deploying standard AI models, use deploy_model instead.

Write operation — recorded in the audit log.

Args: cluster_name: Target cluster. release_name: Helm release name (created if it does not exist). chart: Helm chart reference (e.g. bitnami/nginx or ./charts/myapp). namespace: Kubernetes namespace (default: 'default'). values: Helm values to override (dict, optional). confirmed: Must be True to proceed. Pass False (default) for a dry-run preview. gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name.

helm_uninstallA

Uninstall a Helm release from a cluster. Destructive — requires confirmed=True.

Removes all Kubernetes resources created by the release.

Write operation — recorded in the audit log.

Args: cluster_name: Target cluster. release_name: Name of the Helm release to remove. namespace: Kubernetes namespace (default: 'default'). confirmed: Must be True to proceed. Pass False (default) for a dry-run preview. gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name.

run_kubectlA

Execute a kubectl command on a cluster.

Use this only for operations not covered by dedicated tools. Prefer scale_deployment to scale pods, deploy_model for model deployments, and helm_upgrade or helm_uninstall for Helm operations.

Reads always pass: get, describe, logs, top, rollout (status, history), api-resources, api-versions, explain, cluster-info, config (view), version, wait, auth (can-i).

Writes (delete, apply, patch, scale, label, cordon, drain, exec, …) pass unless the organisation's tool policy turned them off (allow_writes on run_kubectl / kubectl_exec in the console's Tool Policy, open by default). The policy engine asks for confirmed=True, records the write in the audit log, and runs it WITHOUT verification — the catalogued action for the same change would carry a proof, so prefer it when one exists. When the organisation turned writes off, the engine refuses the write by name, whatever the caller.

Args: cluster_name: Target cluster. command: kubectl arguments as a list, without the 'kubectl' prefix. Example: ["get", "pods", "-n", "default"] gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name. confirmed: Required for a write. Pass False (default) to receive the confirmation request with its preview, or the refusal.

git_cloneA

Clone a git repository onto the VibOps gateway.

If cluster_name is provided, Kubernetes manifests found in the repository will be automatically applied to that cluster (kubectl apply). If cluster_name is omitted, the repository is cloned but nothing is applied.

Write operation — recorded in the audit log.

Args: repo_url: Git repository URL (HTTPS or SSH). branch: Branch to clone (default: main). cluster_name: If provided, apply manifests to this cluster after cloning. gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name.

create_secretA

Store an encrypted secret in the VibOps vault.

The value is encrypted at rest and never returned by the API after storage. If a secret with the same name already exists, it is overwritten.

Write operation — recorded in the audit log.

Args: name: Secret name (used to reference this secret in job payloads). value: Secret value (encrypted, never logged or returned). description: Optional description of what this secret is for.

trigger_pipelineA

Manually trigger an automation pipeline.

Pipelines are sequences of jobs that execute in order. Retrieve available pipeline IDs with list_pipelines.

Write operation — recorded in the audit log.

Args: pipeline_id: UUID of the pipeline to trigger. payload: Optional input parameters passed to the pipeline steps.

slurm_get_cluster_infoA

Get Slurm cluster information: partitions, node states, and GPU availability.

Returns a summary of all nodes, their GPU resources (GRES), memory, and current state (idle / allocated / down).

Args: host: Slurm head node hostname. Overrides the SLURM_HOST env var on the gateway. partition: Filter output to a specific partition (optional). gateway_id: Gateway UUID for the site where the Slurm cluster is deployed.

slurm_list_jobsA

List running and pending Slurm jobs.

Returns job ID, name, user, state, partition, node count, GPU allocation, submit time, and time limit for each job.

Args: host: Slurm head node hostname (overrides SLURM_HOST). user: Filter by username (optional). partition: Filter by partition name (optional). state: Filter by job state — RUNNING, PENDING, FAILED, COMPLETED (optional). gateway_id: Gateway UUID for the target site.

slurm_get_job_statusA

Get the current status and resource usage of a specific Slurm job.

Queries squeue for running/pending jobs and falls back to sacct for completed or failed jobs.

Args: job_id: Slurm job ID. host: Slurm head node hostname (overrides SLURM_HOST). gateway_id: Gateway UUID for the target site.

slurm_get_job_outputA

Tail the stdout log file of a Slurm job to monitor training progress.

Reads the last N lines of the job's output file. If log_path is omitted, defaults to slurm-{job_id}.out in the user's home directory.

Args: job_id: Slurm job ID. host: Slurm head node hostname (overrides SLURM_HOST). log_path: Explicit path to the log file (optional). lines: Number of lines to return (default: 50). gateway_id: Gateway UUID for the target site.

slurm_submit_jobA

Submit a multi-node GPU training job to Slurm via sbatch.

Generates a complete sbatch script from the provided spec and submits it. Set dry_run=true to preview the script without submitting.

Write operation — recorded in the audit log.

Args: job_name: Job name (--job-name). nodes: Number of nodes to allocate (--nodes). gpus_per_node: GPUs per node (--gpus-per-node). script: Shell script body — the command to run (e.g. torchrun --nproc_per_node=8 train.py). host: Slurm head node hostname (overrides SLURM_HOST). partition: Target Slurm partition (--partition). ntasks_per_node: MPI tasks per node (default: gpus_per_node). time: Wall-clock time limit in HH:MM:SS or D-HH:MM:SS format (--time). output: Path to stdout log file (default: slurm-%j.out). error: Path to stderr log file (default: slurm-%j.err). account: Slurm account / allocation for billing (--account). dry_run: If true, return the sbatch script without submitting. gateway_id: Gateway UUID for the site where the Slurm cluster is deployed.

slurm_cancel_jobA

Cancel a running or pending Slurm job by job ID (scancel).

Write operation — recorded in the audit log.

Args: job_id: Slurm job ID to cancel. host: Slurm head node hostname (overrides SLURM_HOST). signal: Signal to send to the job (default: SIGTERM). Use SIGKILL for immediate termination. gateway_id: Gateway UUID for the target site.

registry_list_reposB

List repositories in a container registry (Harbor, ECR, or Google Artifact Registry).

Args: registry_type: Registry backend — "harbor", "ecr", or "gar". registry_url: Harbor base URL (e.g. https://registry.acme.com) or ECR registry URI. project: Harbor project name or GAR repository path prefix. username: Harbor username (or "AWS" for ECR token auth). password: Harbor password or registry token. region: AWS region (ECR only, e.g. us-east-1). limit: Maximum number of repositories to return (default 50). gateway_id: Gateway UUID for the target site.

registry_list_tagsB

List all tags for a specific image in a container registry.

Args: registry_type: Registry backend — "harbor", "ecr", or "gar". image: Image name without tag (e.g. "myproject/myapp" for Harbor, repo name for ECR). registry_url: Harbor base URL or ECR registry URI. username: Harbor username or registry token username. password: Harbor password or registry token. region: AWS region (ECR only). gateway_id: Gateway UUID for the target site.

registry_check_imageA

Check whether a specific image:tag exists in a container registry.

Returns exists=True/False without raising an error when the image is absent. Useful for pre-deployment checks and stale image detection.

Args: registry_type: Registry backend — "harbor", "ecr", or "gar". image: Image name with tag (e.g. "myproject/myapp:v1.2.3"). registry_url: Harbor base URL or ECR registry URI. username: Harbor username or registry token username. password: Harbor password or registry token. region: AWS region (ECR only). gateway_id: Gateway UUID for the target site.

registry_delete_tagA

Delete an image tag from a container registry. Destructive — requires confirmed=True.

Permanently removes the specified tag. The underlying image layers are deleted only if no other tag references them. Requires operator role in VibOps.

Write operation — recorded in the audit log.

Args: registry_type: Registry backend — "harbor", "ecr", or "gar". image: Image name with tag to delete (e.g. "myproject/myapp:old-tag"). registry_url: Harbor base URL or ECR registry URI. username: Harbor username or registry token username. password: Harbor password or registry token. region: AWS region (ECR only). confirmed: Must be True to proceed. Pass False (default) for a dry-run preview. gateway_id: Gateway UUID for the target site.

proxmox_list_vmsB

List all VMs on a Proxmox cluster. Filter by node or status (running/stopped/all).

proxmox_start_vmC

Start a stopped Proxmox VM.

proxmox_stop_vmC

Gracefully shutdown a running Proxmox VM.

proxmox_migrate_vmC

Live-migrate a Proxmox VM to another node.

proxmox_create_snapshotC

Create a snapshot of a Proxmox VM.

xo_list_vmsC

List all VMs on XCP-ng pools managed by Xen Orchestra.

xo_start_vmC

Start a halted XCP-ng VM.

xo_stop_vmC

Cleanly shutdown a running XCP-ng VM.

xo_migrate_vmC

Live-migrate an XCP-ng VM to another host.

xo_snapshot_vmC

Create a snapshot of an XCP-ng VM.

xo_v2v_list_esxiB

List ESXi hosts configured in Xen Orchestra for V2V migration.

Returns the ESXi servers that XO can connect to for importing VMware VMs into XCP-ng. Add ESXi servers in XO → Settings → Servers.

Args: gateway_id: Target gateway (optional).

xo_v2v_list_vmware_vmsB

List VMs on a VMware ESXi host available for V2V migration to XCP-ng.

Args: esxi_id: ESXi server ID (from xo_v2v_list_esxi). gateway_id: Target gateway (optional).

xo_v2v_migrateA

Migrate a VM from VMware ESXi to XCP-ng using V2V warm migration.

Warm migration streams disk data while the source VM is still running, then performs a brief cutover (seconds of downtime). Works with all ESXi versions including VMFS6 and VSAN.

Write operation — recorded in the audit log.

Args: esxi_id: Source ESXi server ID. vm_name: Name of the VM to migrate on ESXi. target_sr: Target storage repository UUID on XCP-ng (optional). target_network: Target network UUID on XCP-ng (optional). gateway_id: Target gateway (optional).

xo_v2v_statusA

Check the status of a running V2V migration (progress %, phase, ETA).

Args: task_id: Migration task ID (returned by xo_v2v_migrate). gateway_id: Target gateway (optional).

xo_list_backupsB

List backup jobs configured in Xen Orchestra.

Shows job name, mode (full, delta, disaster recovery), and enabled status.

Args: gateway_id: Target gateway (optional).

xo_run_backupB

Trigger a backup job immediately.

Write operation — recorded in the audit log.

Args: job_id: Backup job ID (from xo_list_backups). gateway_id: Target gateway (optional).

xo_restore_backupC

Restore a VM from an XO backup.

Write operation — recorded in the audit log.

Args: backup_id: Backup ID to restore. target_sr: Target storage repository UUID (optional). gateway_id: Target gateway (optional).

xo_list_srsB

List storage repositories (SRs) across all XCP-ng pools.

Returns capacity, usage, free space and usage percentage for each SR.

Args: gateway_id: Target gateway (optional).

xo_list_tasksA

List running and recent tasks in Xen Orchestra.

Shows migrations, backups, snapshots, and other operations in progress with their status and progress percentage.

Args: gateway_id: Target gateway (optional).

xo_rolling_pool_updateA

Start a rolling pool update — patches all XCP-ng hosts one by one.

VMs are automatically live-migrated to other hosts before each host is patched and rebooted. Zero downtime for running workloads.

Write operation — recorded in the audit log.

Args: pool_id: XCP-ng pool UUID (from xo_list_pools). gateway_id: Target gateway (optional).

vsphere_list_vmsB

List all VMs in the vCenter inventory. Filter by power_state (all/poweredOn/poweredOff/suspended), datacenter, or cluster.

vsphere_get_vmC

Get detailed information about a specific vSphere VM by name.

vsphere_start_vmC

Power on a vSphere VM.

vsphere_stop_vmB

Shut down a vSphere VM. Attempts guest shutdown via VMware Tools by default; set force=True for immediate hard power-off.

vsphere_restart_vmB

Restart a vSphere VM. Attempts guest reboot via VMware Tools by default; set force=True for immediate hard reset.

vsphere_migrate_vmA

Live-migrate (vMotion) a vSphere VM to another ESXi host. Set dry_run=True to validate without moving.

vsphere_create_snapshotC

Create a snapshot of a vSphere VM. Quiescing is attempted automatically when VMware Tools is running.

vsphere_list_hostsC

List all ESXi hosts in the vCenter inventory with CPU, memory, and connection state.

vsphere_get_vm_metricsB

Get real-time CPU, memory, disk, and network metrics for a vSphere VM.

vme_list_instancesA

List all VMs managed by HPE VM Essentials (Morpheus).

Returns name, status, cloud/zone, service plan, CPU and memory for each instance. HPE VME manages both KVM-native VMs and imported VMware VMs from the same console.

Args: status: Filter by VM status — "running", "stopped", or "all" (default). cloud: Filter by cloud/zone name (optional). gateway_id: Target gateway (optional if only one VME gateway exists).

vme_get_instanceA

Get detailed status and configuration of a specific HPE VME instance.

Returns CPU, memory, disk, network, cloud assignment, service plan, creation date and IP address.

Args: instance_id: Morpheus instance ID (from vme_list_instances). gateway_id: Target gateway (optional).

vme_list_serversA

List all physical hosts managed by HPE VME with CPU, memory and status.

Args: cloud: Filter by cloud/zone name (optional). gateway_id: Target gateway (optional).

vme_list_cloudsC

List all clouds/zones configured in HPE VME.

A cloud in Morpheus represents a hypervisor target: KVM (VME native), VMware vSphere, or any other supported provider. This shows what infrastructure VME is managing.

Args: gateway_id: Target gateway (optional).

vme_start_instanceB

Start a stopped HPE VME instance.

Write operation — recorded in the audit log.

Args: instance_id: Morpheus instance ID. gateway_id: Target gateway (optional).

vme_stop_instanceB

Stop a running HPE VME instance (graceful shutdown).

Write operation — recorded in the audit log.

Args: instance_id: Morpheus instance ID. gateway_id: Target gateway (optional).

vme_restart_instanceC

Restart an HPE VME instance.

Write operation — recorded in the audit log.

Args: instance_id: Morpheus instance ID. gateway_id: Target gateway (optional).

vme_create_snapshotA

Create a snapshot of an HPE VME instance. Use before migrations or risky changes.

Write operation — recorded in the audit log.

Args: instance_id: Morpheus instance ID. name: Snapshot name (e.g. "pre-migration-2026-09-09"). gateway_id: Target gateway (optional).

vme_list_snapshotsC

List all snapshots for an HPE VME instance.

Args: instance_id: Morpheus instance ID. gateway_id: Target gateway (optional).

vme_convert_imageA

Convert a virtual image to a different disk format.

Key tool for VMware-to-VME migrations: converts VMDK images to QCOW2 (KVM-native format) without manual intervention. The conversion runs asynchronously on the Morpheus appliance.

Write operation — recorded in the audit log.

Args: image_id: Virtual image ID (from vme_list_virtual_images). format: Target format — "qcow2", "vmdk", "raw", or "vhd". gateway_id: Target gateway (optional).

vme_list_virtual_imagesA

List available virtual images in HPE VME (templates, ISOs, uploaded images).

Use before vme_convert_image to find the image ID of a VMware VMDK that needs conversion for migration.

Args: image_type: Filter by type (optional). gateway_id: Target gateway (optional).

vme_detect_vm_wasteB

Detect VM waste in HPE VME: stopped instances and over-provisioned VMs.

Returns actionable recommendations with severity levels. Use for FinOps reviews and cost optimisation.

Args: stopped_days_threshold: Flag VMs stopped for more than N days (default: 7). gateway_id: Target gateway (optional).

vme_get_activityC

Get recent activity/audit log from HPE VME — provisioning, changes, logins.

Args: max: Max results (default: 50). gateway_id: Target gateway (optional).

set_cluster_rateA

Set the GPU cost rate for a cluster.

Required to enable cost estimates (get_cost_estimate). Can be updated at any time. Requires organisation admin role.

Write operation — recorded in the audit log.

Args: cluster_name: Name of the cluster. rate_per_gpu_hour: Cost per GPU per hour (e.g. 2.50 for $2.50/GPU/hr). currency: ISO 4217 currency code (default: USD).

register_gatewayA

Register a new VibOps gateway (remote agent).

Returns a one-time bearer token to configure the gateway with — store it immediately, it cannot be retrieved again.

Write operation — recorded in the audit log.

Args: name: Human-readable name for the gateway (e.g. 'prod-vpc', 'eu-west-dc'). description: Optional description of the gateway's location or purpose. clusters: List of cluster names this gateway will manage.

delete_gatewayA

Revoke a VibOps gateway and invalidate its token.

The gateway will immediately lose the ability to poll for jobs. Existing jobs assigned to this gateway will fail.

Write operation — recorded in the audit log.

Args: gateway_id: UUID of the gateway to revoke.

list_anomaliesA

List GPU anomalies detected by VibOps across all clusters.

Anomalies are detected automatically every 5 minutes: gpu_idle (<10 % utilisation), gpu_spike (>90 %), node_loss (node disappeared from scrape), utilization_drop (>30 pt drop in one window). Duplicates are suppressed — only one open event per anomaly type per cluster exists at a time.

Args: cluster_name: Filter by cluster name (optional). status: Filter by status — "open" or "resolved" (optional, returns all if omitted).

get_open_anomaliesA

Return all currently open (unresolved) GPU anomalies across the fleet.

Use this for a quick fleet health check alongside list_alerts. An open anomaly means the triggering condition is still active. Resolution is automatic once the condition disappears, or manual via resolve_anomaly.

resolve_anomalyA

Manually mark an anomaly as resolved.

Use when the underlying issue has been addressed outside VibOps (e.g. a workload was restarted manually). Automatic resolution still applies when the condition normalises on the next detection cycle.

Write operation — recorded in the audit log.

Args: anomaly_id: UUID of the anomaly to resolve (from list_anomalies). reason: Optional free-text explanation of how the issue was resolved.

list_compliance_controlsA

List compliance controls and their current status.

Supports 19 regulatory frameworks: ai_act, gdpr, uk_gdpr, fadp, bdsg, kvkk, pdpl_saudi, appi, dpa_philippines, privacy_act_au, hipaa, ccpa, lfpdppp, pipl, dpdp, lgpd, pipeda, pdpa_singapore, pipa_korea.

Each control has a framework, article, title, status (compliant / partial / non_compliant / not_applicable), optional notes, and an evidence URL.

Use get_compliance_score to get the aggregated compliance percentage.

Args: framework: Filter by regulatory framework key (optional, returns all if omitted).

get_compliance_scoreA

Return the organisation's compliance score (0–100) for a framework.

Score is the weighted average of applicable controls: compliant=1.0, partial=0.5, non_compliant=0.0. Controls marked not_applicable are excluded from the denominator so they do not penalise the score.

Use list_compliance_controls to see per-article breakdown and identify gaps.

Args: framework: Regulatory framework key (optional — omit for aggregate across all).

update_compliance_controlA

Update the status, notes or evidence URL of a compliance control.

Works across all frameworks (AI Act, GDPR, PDPL, HIPAA, etc.). Write operation — recorded in the audit log.

Args: control_id: UUID of the control to update (from list_compliance_controls). status: New compliance status — one of: compliant, partial, non_compliant, not_applicable. notes: Free-text justification or implementation notes (optional). evidence_url: URL to supporting evidence document or test report (optional).

list_compliance_reportsA

List generated compliance reports for the organisation.

Reports are generated asynchronously; status moves from "pending" to "ready" (or "failed") once the audit log analysis completes. Use get_compliance_report to retrieve the full findings once ready.

Args: report_type: Filter by framework — "soc2", "gdpr", or "hipaa" (optional).

generate_compliance_reportA

Trigger generation of a compliance report by analysing the audit log.

Generation is asynchronous — this call returns immediately with a report object in "pending" status. Poll get_compliance_report until status is "ready". Generation time depends on audit log volume for the period.

Write operation — recorded in the audit log.

Args: report_type: Compliance framework — "soc2", "gdpr", or "hipaa". period: Time period to analyse. Formats accepted: "2026-Q1" (quarter), "2026-05" (month), "2026" (full year).

get_compliance_reportA

Retrieve a compliance report by ID, including its findings once ready.

Poll this after generate_compliance_report until status == "ready". The "summary" field contains per-control findings, counts of passing / failing events, and remediation recommendations.

Args: report_id: UUID of the report (from generate_compliance_report or list_compliance_reports).

list_audit_logsA

Query the immutable VibOps audit log.

Every operation (deploy, scale, policy change, identity rotation…) is recorded with full context: actor, org, cluster, parameters, result, duration, cost. Entries are HMAC-chained — use verify_audit_chain to confirm integrity.

Args: from_dt: Start of time window, ISO 8601 (e.g. "2026-05-01T00:00:00Z"). Optional. to_dt: End of time window, ISO 8601. Optional. action: Filter by action type (e.g. "helm_upgrade", "scale_cluster"). Optional. limit: Maximum number of entries to return (default 50, max 500).

verify_audit_chainA

Verify the cryptographic integrity of the entire audit log chain.

Each audit entry is signed with HMAC-SHA256 chaining the previous entry's hash. This endpoint traverses the full chain and reports the first broken link if tampering is detected, or confirms the chain is intact.

Returns: {"valid": true} if the chain is intact, or {"valid": false, "broken_at": <entry_id>, "detail": "..."} if corruption is found.

get_policyA

Return the active policy configuration for the current organisation.

Policy controls: allowed LLM models, budget limits per agent, tool permission matrix, rate limits, escalation rules and default-deny behaviour. Changes take effect immediately on all active agents.

update_policyA

Replace the organisation policy configuration.

The full policy object must be supplied (not a partial patch). Retrieve the current policy with get_policy, modify the desired fields, then submit. Changes are applied immediately — active agents will reflect the new policy within seconds. All changes are recorded in the audit log.

Write operation — recorded in the audit log.

Args: policy: Complete policy object as returned by get_policy, with modifications applied. Unknown keys are rejected.

list_agent_identitiesA

List all agent machine identities for the organisation.

Each identity has a name, key prefix (vib_…), creation date, last-used timestamp, rotation history, and revocation status. The raw key is never stored — only its SHA-256 hash is retained after creation.

Use create_agent_identity to issue a new identity for a service or agent.

create_agent_identityA

Create a new agent machine identity and return its API key.

The raw key is returned ONCE in this response and never again — store it securely immediately. The key is prefixed with "vib_" and stored as a SHA-256 hash in VibOps. If the key is lost, rotate the identity instead of recreating it.

Write operation — recorded in the audit log.

Args: name: Human-readable label for this identity (e.g. "pricing-agent-prod"). expires_at: Optional expiry date in ISO 8601 format (e.g. "2027-01-01T00:00:00Z"). If omitted, the identity does not expire.

rotate_agent_identityA

Rotate the API key for an agent identity.

Generates a new key and immediately invalidates the previous one. The new raw key is returned ONCE in this response — store it securely. The identity itself (ID, name, history) is preserved; only the key changes.

Use this for scheduled key rotation or if a key is suspected of being compromised. To permanently disable an identity, use revoke_agent_identity.

Write operation — recorded in the audit log.

Args: identity_id: UUID of the identity to rotate (from list_agent_identities).

revoke_agent_identityA

Permanently revoke an agent identity, blocking all future authentication.

Revocation is immediate and irreversible. The identity record is retained for audit purposes but the key is rejected on all subsequent API calls. Use rotate_agent_identity instead if you simply want to cycle the key.

Write operation — recorded in the audit log.

Args: identity_id: UUID of the identity to revoke (from list_agent_identities).

get_agent_dependency_graphA

Return the full directed dependency graph for all agents in the organisation.

Edges represent runtime relationships: agent→model (which LLM an agent calls), agent→connector (which data sources it uses), agent→agent (which sub-agents it orchestrates). Each edge records call_count, first_seen and last_seen timestamps.

Key use case: impact analysis — "if I replace this LLM model, which agents are affected and how frequently do they call it?"

get_agent_dependenciesA

Return the dependency edges for a single agent.

Shows what models, connectors and sub-agents this agent depends on, with call counts and timestamps. Use get_agent_dependency_graph for the full organisation-wide view.

Args: agent_id: ID or name of the agent (as registered in the tool catalogue).

list_eval_rubricsA

List LLM-as-judge evaluation rubrics defined for the organisation.

A rubric defines evaluation criteria (accuracy, safety, relevance…), a scoring grid (0–10 with justification), and the LLM provider used as judge (Claude, OpenAI, Ollama, Groq). Rubrics marked is_auto_scanner=true trigger automatically after every completed job.

evaluate_jobA

Trigger an LLM-as-judge evaluation of a completed job against a rubric.

The evaluation runs asynchronously: the judge LLM scores the job's input/output against each criterion in the rubric and produces a numeric score with a textual justification. Results are retrievable via get_job_evaluations.

Write operation — recorded in the audit log.

Args: job_id: UUID of the job to evaluate (must be in "success" or "failed" state). rubric_id: UUID of the rubric to apply (from list_eval_rubrics).

get_job_evaluationsA

Return all LLM-as-judge evaluation results for a specific job.

Each evaluation includes: rubric applied, overall score (0–10), per-criterion breakdown, textual justification from the judge LLM, evaluation timestamp and the provider used. A job may have multiple evaluations if different rubrics were applied or if it was re-evaluated.

Args: job_id: UUID of the job (from list_jobs or get_job).

get_ldap_configA

Return the LDAP / Active Directory authentication configuration for the current organisation.

Shows whether LDAP is enabled, the server URL, bind DN, search base, search filter, JIT provisioning flag, and default role. The bind password is never returned — ldap_bind_password_set indicates whether one is stored.

update_ldap_configA

Update the LDAP / Active Directory configuration for the current organisation.

Only supplied fields are updated — omitted fields are left unchanged. To enable LDAP (ldap_enabled=True), ldap_server_url, ldap_bind_dn, ldap_bind_password, and ldap_search_base must already be set (or provided in the same call). Requires org_admin role.

Search filter examples: OpenLDAP : (uid={username}) Active Directory: (sAMAccountName={username}) Azure AD on-prem: (userPrincipalName={username}@domain.com)

Args: ldap_server_url: LDAP server URL, e.g. ldap://dc.corp.local or ldaps://dc.corp.local. ldap_bind_dn: Service account DN, e.g. cn=svc-vibops,ou=users,dc=corp,dc=local. ldap_bind_password: Service account password (stored Fernet-encrypted). ldap_search_base: Search base DN, e.g. ou=users,dc=corp,dc=local. ldap_search_filter: User search filter with {username} placeholder (default: (uid={username})). ldap_default_role: Role assigned to JIT-provisioned users — member, admin, or viewer. ldap_jit_provisioning: If True, unknown users are auto-provisioned on first login. ldap_enabled: Set True to activate LDAP login, False to disable without clearing config.

get_siem_configA

Return the SIEM push export configuration for the current organisation.

Shows the configured provider (splunk or datadog), the destination endpoint, and whether a token is stored. The token itself is never returned.

update_siem_configA

Configure the SIEM push export destination for the current organisation.

Only supplied fields are updated. Requires org_admin role.

Splunk: siem_provider="splunk", siem_endpoint="https://splunk.corp.local:8088", siem_token="" Datadog: siem_provider="datadog", siem_endpoint="datadoghq.com" (or datadoghq.eu), siem_token=""

Once configured, use push_to_siem to push audit events on demand.

Args: siem_provider: Destination type — "splunk" or "datadog". siem_endpoint: Splunk HEC base URL or Datadog site (e.g. datadoghq.com). siem_token: Splunk HEC token or Datadog API key (stored Fernet-encrypted).

push_to_siemA

Push audit log events to the configured SIEM (Splunk HEC or Datadog Logs API).

Sends matching audit rows to the SIEM in a single batched request. Returns the number of events pushed and the provider used. Requires org_admin role and a configured SIEM destination (update_siem_config).

The pull-based export (GET /audit/export?format=cef|leef|json) remains available as an alternative for batch ingestion.

Args: since: ISO 8601 start timestamp (e.g. 2026-06-01T00:00:00Z). Defaults to all history. until: ISO 8601 end timestamp. Defaults to now. action: Filter by action name (e.g. "scale_cluster", "deploy_model"). limit: Maximum number of events to push (default 10 000).

get_agent_model_rulesA

List all active agent model access rules for the organisation.

Rules control which LLM models each agent is allowed to use. Uses glob patterns for agent_id matching (e.g. "data-pipeline-") and model matching (e.g. "llama-"). Deny takes precedence over allow.

update_agent_model_ruleA

Create a new agent model access rule. Controls which LLM models an agent can use through the VibOps LLM proxy.

Examples:

  • Allow pricing agents only Llama models: pattern="pricing-", allowed=["llama-"]

  • Block all agents from GPT-4o: pattern="", denied=["gpt-4o"]

Args: agent_id_pattern: Glob pattern matching agent IDs (e.g. "pricing-", ""). allowed_models: List of model glob patterns the agent MAY use. Empty = all allowed. denied_models: List of model glob patterns the agent MUST NOT use. Deny overrides allow.

get_budgetA

Return the current GPU budget configuration and consumption for the organisation.

Shows budget limits (tokens, cost in USD/EUR), current consumption for the active period, percentage used, and the behaviour configured at the limit (queue / throttle / reject). Use set_cluster_rate to configure per-GPU hourly rates before relying on cost figures.

get_chargebackA

Return the chargeback report for a given month, broken down by tenant and agent.

Chargeback allocates GPU costs to cost centres based on elapsed_hours × gpu_count × ClusterRate per workload. Useful for inter-department billing or to validate cloud invoices against actual AI workload consumption.

Args: year: Four-digit year (e.g. 2026). month: Month number 1–12 (e.g. 5 for May).

get_spend_trendA

Return GPU spend trend over the specified number of days.

Provides daily cost series per cluster and per tenant, enabling detection of cost regressions after new deployments. Anomalous spikes are flagged automatically. Requires cluster rates to be configured via set_cluster_rate.

Args: days: Lookback window in days (default 30, max 90).

get_waste_analysisA

Return GPU waste analysis — idle resources consuming budget without doing work.

Identifies: GPU nodes with <10 % utilisation over the past 24 h, deployments with zero jobs in the past 7 days, over-provisioned replicas relative to queue depth. Each finding includes an estimated wasted cost and a recommended remediation action (scale down, suspend, or reassign).

get_agent_usageA

Return LLM inference usage aggregated by agent — token consumption, GPU cost, and request counts. Use this to understand which AI agents are consuming the most inference resources and how costs distribute across teams.

This is the only tool that bridges agent-level identity with GPU-level cost. Typical questions it answers:

  • "Which agent costs the most in GPU this month?"

  • "How much does the pricing agent spend on Llama-70B vs Mistral-7B?"

  • "Which team is over budget on LLM inference?"

Args: period: Lookback period — "7d", "30d", or "mtd" (month-to-date). Default "30d". agent_id: Filter to a specific agent (optional). team: Filter to a specific team (optional). model: Filter to a specific LLM model (optional).

get_agent_usage_detailA

Return detailed LLM inference usage for a specific agent — daily breakdown, model distribution, cost trend, and optimisation recommendations.

Use after get_agent_usage identifies an agent of interest. Shows:

  • Daily request count, token usage, and cost over the last 30 days

  • Breakdown by LLM model (which models this agent uses and how much each costs)

  • Cost trend (increasing / stable / decreasing)

Args: agent_id: The agent identifier (as reported via X-VibOps-Agent-Id header).

get_agent_budgetB

Return the inference budget for a specific agent — monthly limit, current spend, and enforcement action (reject/warn).

Args: agent_id: The agent identifier.

set_agent_budgetA

Set or update the monthly inference budget for an agent. When the agent exceeds the hard cap, the LLM proxy blocks further requests (429).

Args: agent_id: The agent identifier. monthly_limit_usd: Monthly spend limit in USD. soft_cap_pct: Percentage at which a warning is emitted (default 80). hard_cap_pct: Percentage at which requests are blocked (default 100). action: Enforcement action at hard cap — "reject" (default) or "warn".

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.2/5.0

Scored across 117 tools

Disambiguation3/5

Most tools group cleanly into domain namespaces (slurm_, registry_, proxmox_, xo_, vsphere_, vme_) with descriptions that cross-reference related tools, so the majority are easy to tell apart. However, real overlaps exist: list_anomalies and get_open_anomalies both surface open anomalies, and the overloaded term 'jobs' spans VibOps operations (list_jobs/get_job), Slurm jobs (slurm_list_jobs), job SLIs (get_job_metrics), and eval results (get_job_evaluations), which invites misselection at 117 tools.

Naming Consistency4/5

The dominant convention is consistent snake_case verb_noun, usually with a domain prefix (slurm_submit_job, registry_list_tags, vsphere_get_vm). Minor deviations exist: helm_upgrade/helm_uninstall reverse to noun_verb, run_kubectl uses a different verb style, and get_vm_usage is un-namespaced despite living beside the prefixed hypervisor tools.

Tool Count1/5

117 tools is an extreme mismatch for any single agent surface, far beyond the 3-15 healthy range. The set aggregates six or more distinct product domains (HPC, registries, four hypervisors, FinOps, compliance, identity, audit), so an agent must navigate a huge selection space for any given task.

Completeness4/5

Coverage across most domains is strong and often full lifecycle: identities (create/list/rotate/revoke), policies (get/update), Slurm (submit/cancel/list/status/output), and per-hypervisor VM start/stop/snapshot/migrate. Gaps remain — pipelines can be listed and triggered but not created or deleted/updated, and secrets can be created and listed but not deleted or rotated.

Maintenance

ActivityActive
ResponsivenessLimited data