vibops-mcp
OfficialAn MCP server that lets an AI assistant observe and operate a GPU/AI infrastructure fleet through VibOps — clusters, deployments, jobs, Slurm, registries, costs, compliance and agent identity — with every write recorded in a tamper-evident audit log.
Observe infrastructure — list clusters and GPU utilisation, live K8s deployment/pod health, gateways, kubectl contexts, providers, pipelines, secrets (names only), alerts and GPU metrics/MTTR.
Track jobs — list/filter VibOps operations, fetch job results and outputs, and get SLI metrics (success rate, p50/p95 latency, hourly sparklines).
Deploy and operate — scale deployments, deploy models, run helm upgrade/uninstall, execute arbitrary kubectl, and clone git repos (optionally applying their manifests).
Manage secrets and automation — store encrypted secrets and trigger multi-step pipelines.
Run HPC workloads — inspect Slurm clusters/partitions/nodes, list and check jobs, tail job output, submit multi-node GPU jobs (with dry-run), and cancel them.
Work with container registries — list repos and tags, check whether an image tag exists, and delete stale tags (confirmed=True).
Administer the platform — set per-cluster GPU cost rates and register/revoke gateways (one-time tokens).
Govern and assure compliance — detect, list and resolve GPU anomalies; manage AI Act controls and scores; generate and retrieve SOC 2/GDPR/HIPAA reports; query the audit log and verify its HMAC-SHA256 chain integrity.
Control agent access and policy — read/replace org policy, define agent→model allow/deny rules, and manage agent machine identities (create, rotate, revoke keys shown once).
Evaluate quality — list LLM-as-judge rubrics, evaluate jobs, and retrieve scored results.
Integrate identity and security tooling — read/update LDAP/AD config and SIEM (Splunk/Datadog) export, plus push audit events on demand.
Do agent-level FinOps — per-agent token/cost/request usage and drill-downs, monthly budgets with soft/hard caps, plus org budget, chargeback, spend trends and waste analysis.
Gap to note: despite the README's 117-tool claim, this schema exposes no hypervisor tools (Proxmox, vSphere, Xen Orchestra) and no HPE VME/Morpheus tools; governance here is AI Act–focused rather than the README's generic compliance-control set.
Allows CrewAI agents to interact with GPU infrastructure for deployment and monitoring.
Allows exporting audit events and GPU metrics to Datadog for monitoring and alerting.
Provides tools for cloning Git repositories as part of deployment workflows.
Provides tools for managing Helm releases on Kubernetes clusters, including upgrade and uninstall operations.
Provides LangChain-based AI agents with tools to observe, operate, and govern GPU clusters.
Enables n8n workflows to manage GPU infrastructure, including deployment, monitoring, and cost optimization.
Allows AI agents to route inference requests through the VibOps proxy to Ollama, with cost attribution and logging.
Supports OpenAI-compatible API for inference, capturing usage data for FinOps.
Allows exporting audit events and GPU metrics to Splunk for security information and event management.
vibops-mcp
The MCP server for VibOps — The AI Infrastructure Engine. From code to GPU in one conversation.
The problem
Getting an AI app from code to production on GPUs requires stitching together 9+ tools — git, Docker, CI/CD, Helm, kubectl, GPU monitoring, cost management, compliance, alerting. Each with its own API, dashboard, and cost model. No single interface spans the full pipeline.
Related MCP server: k8s-aiops
The solution
vibops-mcp connects your AI assistant to VibOps — the engine that clones, builds, deploys, scales, monitors, fixes, and bills your apps and agents on any GPU, any cluster, any cloud. One pip install, 117 tools, one conversation.
Ship — clone repos, build containers, deploy models, run Helm/kubectl, trigger pipelines, submit Slurm jobs
Operate — scale deployments, manage VMs (Proxmox/XO/vSphere/HPE VME), detect and remediate GPU anomalies
Observe — GPU utilisation, workload breakdown, MTTR, cost estimates, live K8s deployments
Govern — AI Act compliance, SOC 2/RGPD reports, immutable audit chain, policy management
FinOps — per-agent cost tracking, budget enforcement, chargeback, spend trends, waste analysis
Every operation goes through your VibOps instance and is recorded in the immutable audit log.
Installation
pip install git+https://github.com/VibOpsai/vibops-mcp.gitReleased versions are also on PyPI, if you prefer a pinned one:
pip install vibops-mcpConfiguration
You need two environment variables:
Variable | Description |
| Base URL of your VibOps instance, e.g. |
| API token — create one in VibOps → Settings → API Tokens |
Connecting your client
vibops-mcp speaks the Model Context Protocol, so the same server entry works
in any MCP-compatible client. Add it to your client's MCP configuration:
{
"mcpServers": {
"vibops": {
"command": "vibops-mcp",
"env": {
"VIBOPS_URL": "https://vibops.example.com",
"VIBOPS_TOKEN": "your-token-here"
}
}
}
}Where that file lives depends on the client:
Client | Configuration file |
Claude Desktop |
|
Cursor |
|
Other MCP clients read the same block from their own configuration file; see your client's documentation for its location. Some ship a command that writes the entry for you instead of editing the file by hand.
Available tools
Observation (16 tools — read-only)
Tool | Description |
| List clusters and GPU utilisation |
| List available kubectl contexts |
| Live K8s deployment status for a cluster |
| Get configured GPU cost rate for a cluster |
| List recent jobs with optional filters |
| Get job details and result |
| Job success rate, latency P50/P95/P99, error breakdown |
| Hourly GPU utilisation time-series |
| Job count by workload type |
| Mean Time To Resolve GPU alerts |
| Estimated GPU spend |
| List registered gateways and status |
| List GPU alerts (open or resolved) |
| List secrets (names only, never values) |
| List configured AI/GPU cloud providers |
| List automation pipelines |
Actions (18 tools — write)
Tool | Description |
| Scale a K8s deployment replica count |
| Deploy an AI model onto a GPU cluster |
| Run helm upgrade --install (destructive — requires confirmed=True) |
| Uninstall a Helm release (destructive — requires confirmed=True) |
| Run an arbitrary kubectl command |
| Clone a git repository |
| Store an encrypted secret |
| Manually trigger an automation pipeline |
| Get Slurm cluster info and partition details |
| List Slurm jobs with optional filters |
| Get status of a specific Slurm job |
| Retrieve stdout/stderr of a completed Slurm job |
| Submit a new Slurm job |
| Cancel a running or pending Slurm job |
| List container registry repositories |
| List tags for a container image |
| Check image details (size, layers, created date) |
| Delete a stale image tag (requires confirmed=True) |
HPE VME / Morpheus (13 tools)
Tool | Description |
| List all VMs managed by HPE VME |
| Get detailed VM status and configuration |
| List physical hosts with CPU/memory |
| List configured clouds/zones (KVM, VMware) |
| Start a stopped instance |
| Stop a running instance |
| Restart an instance |
| Create a snapshot (pre-migration) |
| List snapshots for an instance |
| Convert disk format (vmdk → qcow2) — VMware migration |
| List available images and templates |
| Detect stopped/idle VMs with recommendations |
| Recent audit log from Morpheus |
Hypervisors — Proxmox, vSphere, Xen Orchestra (30 tools)
Documented last and listed here in full: these were registered and served but absent from this README, so a reader counting the sections found 87 of the 117 the first line promises. They now add up.
Proxmox VE (5 tools)
Tool | Description |
| List VMs across the cluster with status and sizing |
| Start a stopped VM |
| Stop a running VM (destructive — requires confirmed=True) |
| Migrate a VM to another node (destructive — requires confirmed=True) |
| Snapshot a VM before a risky change |
VMware vSphere (9 tools)
Tool | Description |
| List VMs with power state, host and resources |
| Read one VM: power state, host, vCPU, RAM, NICs |
| CPU, memory and disk usage for one VM |
| List ESXi hosts with capacity |
| Power a VM on |
| Shut a VM down (destructive — requires confirmed=True) |
| Restart a VM (destructive — requires confirmed=True) |
| vMotion a VM to another host (destructive — requires confirmed=True) |
| Snapshot a VM |
Xen Orchestra / XCP-ng (15 tools)
Tool | Description |
| List VMs across all pools |
| Start a VM |
| Cleanly shut a VM down (destructive — requires confirmed=True) |
| Migrate a VM to another host (destructive — requires confirmed=True) |
| Snapshot a VM |
| List storage repositories — capacity planning before a migration |
| Running XO tasks |
| List configured backup jobs |
| Run a backup job now |
| Restore a VM from a backup (destructive — requires confirmed=True) |
| Patch every host in the pool, one at a time (destructive — requires confirmed=True) |
| List reachable ESXi hosts, for a VMware migration |
| List the VMs on an ESXi host |
| Migrate a VMware VM onto XCP-ng (destructive — requires confirmed=True) |
| Follow a V2V migration in progress |
Cross-hypervisor
Tool | Description |
| VM usage and cost across every declared hypervisor |
Configuration (3 tools)
Tool | Description |
| Set GPU cost rate for a cluster (admin only) |
| Register a new gateway (returns one-time token) |
| Revoke a gateway |
Agent Infrastructure Control Plane (12 tools)
The missing layer between your AI agents and your GPU fleet. Works with any framework (n8n, LangChain, CrewAI, Dify) — just point to the VibOps LLM Proxy.
Tool | Description |
FinOps per agent | |
| GPU cost per agent — tokens, requests, cost, GPU-hours. "Which agent costs the most?" |
| Drill-down on one agent — daily breakdown, model distribution, cost trend |
| Current budget + MTD spend for an agent |
| Set monthly spend limit — soft alert at 80%, hard block at 100% (HTTP 429) |
Model access control | |
| List model access rules — which agent can use which LLM |
| Create a rule: glob patterns, deny-first. "RH agents → Mistral only" |
Identity lifecycle | |
| List machine identities for agents |
| Create a new machine identity (key shown once) |
| Rotate the key for an existing identity |
| Revoke an identity immediately |
Dependency graph | |
| Full org-wide graph: agent→model, agent→connector, agent→sub-agent |
| Dependencies for one agent — impact analysis before migration |
Governance & Compliance (21 tools)
Tool | Description |
| List GPU anomalies with optional cluster/status filter |
| Get all currently open anomalies |
| Mark an anomaly as resolved |
| List compliance controls (filter by framework) |
| Get the compliance score for a framework (or all) |
| Update status, notes, or evidence URL for a control |
| List generated compliance reports |
| Generate a SOC 2, RGPD, or HIPAA report asynchronously |
| Poll/retrieve a generated compliance report |
| Query the immutable audit log with filters |
| Verify HMAC-SHA256 integrity of the full audit chain |
| Get the current organisation policy |
| Replace the organisation policy (immediate effect) |
| List LLM-as-judge evaluation rubrics |
| Trigger LLM-as-judge evaluation for a job |
| Retrieve evaluation results for a job |
| Get LDAP / Active Directory configuration |
| Configure or enable/disable LDAP integration |
| Get SIEM push export configuration |
| Set Splunk/Datadog SIEM destination |
| Export audit events to configured SIEM |
GPU FinOps (4 tools)
Tool | Description |
| Get current GPU budget and consumed spend |
| Get chargeback breakdown by tenant for a given month |
| Get daily GPU spend trend (default: last 30 days) |
| Identify idle GPU resources and cost optimisation opportunities |
LLM Inference Proxy
VibOps includes a transparent OpenAI-compatible proxy (port 8004) that sits between your AI agents and LLM inference servers (vLLM, Ollama, TGI). Every inference request is logged with agent attribution for FinOps.
Your agents point to the proxy instead of the LLM directly:
# Before
OPENAI_BASE_URL=http://vllm:8000/v1
# After
OPENAI_BASE_URL=http://vibops-proxy:8004/v1Add a X-VibOps-Agent-Id header to attribute costs per agent:
curl -X POST http://vibops-proxy:8004/v1/chat/completions \
-H "X-VibOps-Agent-Id: pricing-agent-v2" \
-H "X-VibOps-Team: supply-chain" \
-d '{"model": "mistral:7b", "messages": [...]}'The proxy captures: agent ID, team, model, tokens, latency, GPU cost — visible in the console FinOps dashboard and queryable via get_agent_usage.
Example prompts
"Clone my repo and deploy it on the GPU cluster."
"Deploy llama3:8b on vibops-dev with 2 replicas."
"Scale the inference deployment to 4 replicas on prod-cluster."
"What's our GPU utilisation trend over the last 7 days?"
"Show me the cost breakdown per cluster this week."
"Which clusters have open critical GPU alerts?"
"Are there any open GPU anomalies right now?"
"Scan my infrastructure and show discovered services."
"What's our AI Act compliance score and which controls are non-compliant?"
"Generate a SOC 2 report for Q1 2026."
"Verify the audit chain hasn't been tampered with."
"Which agent costs the most in GPU this month?"
"Show me the inference cost breakdown for the pricing agent."
"Which agents share the same model, and what does each one cost?"
"Create a machine identity for the pricing-agent with a 1-year expiry."
"Show me the spend trend for the last 7 days and flag any waste."Contributing
See CONTRIBUTING.md. All contributions require a DCO sign-off (git commit -s).
License
MIT — free to use, modify, and distribute. See LICENSE.
Available Tools
117 toolscreate_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.
Inputs: name (required), expires_at.
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.
Inputs: name (required), value (required), description.
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.
Inputs: gateway_id (required).
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.
Inputs: model_name (required), cluster_name (required), env, image, +4 more.
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).
Inputs: job_id (required), rubric_id (required).
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).
Inputs: period (required), report_type (required).
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.
Inputs: agent_id (required).
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).
Inputs: agent_id (required).
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?"
Inputs: no named parameters.
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.
Inputs: no named parameters.
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).
Inputs: team, model, period, agent_id.
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).
Inputs: agent_id (required).
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.
Inputs: no named parameters.
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).
Inputs: year (required), month (required).
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).
Inputs: cluster_name (required), namespace.
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.
Inputs: cluster_name (required).
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).
Inputs: report_id (required).
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).
Inputs: framework.
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).
Inputs: hours.
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).
Inputs: hours.
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.
Inputs: job_id (required).
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).
Inputs: job_id (required).
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).
Inputs: hours.
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.
Inputs: no named parameters.
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).
Inputs: hours.
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.
Inputs: no named parameters.
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.
Inputs: no named parameters.
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.
Inputs: no named parameters.
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).
Inputs: days.
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.
Inputs: no named parameters.
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).
Inputs: no named parameters.
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).
Inputs: hours.
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.
Inputs: repo_url (required), branch, gateway_id, 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.
Inputs: cluster_name (required), release_name (required), confirmed, namespace, +1 more.
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.
Inputs: chart (required), cluster_name (required), release_name (required), values, +3 more.
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.
Inputs: no named parameters.
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.
Inputs: resolved, severity.
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).
Inputs: status, cluster_name.
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).
Inputs: limit, to_dt, action, from_dt.
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.
Inputs: no named parameters.
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).
Inputs: framework.
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).
Inputs: report_type.
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.
Inputs: no named parameters.
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.
Inputs: no named parameters.
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).
Inputs: limit, action, status.
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.
Inputs: no named parameters.
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).
Inputs: limit.
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.
Inputs: no named parameters.
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).
Inputs: search.
proxmox_create_snapshotC
Create a snapshot of a Proxmox VM.
Inputs: name (required), node (required), vmid (required), gateway_id.
proxmox_list_vmsB
List all VMs on a Proxmox cluster. Filter by node or status (running/stopped/all).
Inputs: node, status, gateway_id.
proxmox_migrate_vmC
Live-migrate a Proxmox VM to another node.
Inputs: node (required), vmid (required), target (required), online, +1 more.
proxmox_start_vmC
Start a stopped Proxmox VM.
Inputs: node (required), vmid (required), gateway_id.
proxmox_stop_vmC
Gracefully shutdown a running Proxmox VM.
Inputs: node (required), vmid (required), gateway_id.
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).
Inputs: limit, since, until, action.
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.
Inputs: name (required), clusters, description.
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.
Inputs: image (required), registry_type (required), region, password, +3 more.
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.
Inputs: image (required), registry_type (required), region, password, +4 more.
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.
Inputs: registry_type (required), limit, region, project, +4 more.
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.
Inputs: image (required), registry_type (required), region, password, +3 more.
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.
Inputs: anomaly_id (required), reason.
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).
Inputs: identity_id (required).
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).
Inputs: identity_id (required).
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.
Inputs: command (required), cluster_name (required), confirmed, gateway_id.
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.
Inputs: replicas (required), cluster_name (required), deployment_name (required), namespace, +1 more.
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".
Inputs: agent_id (required), monthly_limit_usd (required), action, hard_cap_pct, +1 more.
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).
Inputs: cluster_name (required), rate_per_gpu_hour (required), currency.
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.
Inputs: job_id (required), host, signal, gateway_id.
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.
Inputs: host, partition, gateway_id.
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.
Inputs: job_id (required), host, lines, log_path, +1 more.
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.
Inputs: job_id (required), host, gateway_id.
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.
Inputs: host, user, state, partition, +1 more.
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.
Inputs: nodes (required), script (required), job_name (required), gpus_per_node (required), +9 more.
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.
Inputs: pipeline_id (required), payload.
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.
Inputs: agent_id_pattern (required), denied_models, allowed_models.
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).
Inputs: status (required), control_id (required), notes, evidence_url.
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.
Inputs: ldap_bind_dn, ldap_enabled, ldap_server_url, ldap_search_base, +4 more.
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.
Inputs: policy (required).
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).
Inputs: siem_token, siem_endpoint, siem_provider.
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.
Inputs: no named parameters.
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).
Inputs: format (required), image_id (required), gateway_id.
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).
Inputs: name (required), instance_id (required), gateway_id.
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).
Inputs: gateway_id, stopped_days_threshold.
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).
Inputs: max, gateway_id.
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).
Inputs: instance_id (required), gateway_id.
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).
Inputs: gateway_id.
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).
Inputs: cloud, status, gateway_id.
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).
Inputs: cloud, gateway_id.
vme_list_snapshotsC
List all snapshots for an HPE VME instance.
Args: instance_id: Morpheus instance ID. gateway_id: Target gateway (optional).
Inputs: instance_id (required), gateway_id.
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).
Inputs: gateway_id, image_type.
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).
Inputs: instance_id (required), gateway_id.
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).
Inputs: instance_id (required), gateway_id.
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).
Inputs: instance_id (required), gateway_id.
vsphere_create_snapshotC
Create a snapshot of a vSphere VM. Quiescing is attempted automatically when VMware Tools is running.
Inputs: name (required), snapshot_name (required), memory, gateway_id, +1 more.
vsphere_get_vmC
Get detailed information about a specific vSphere VM by name.
Inputs: name (required), gateway_id.
vsphere_get_vm_metricsB
Get real-time CPU, memory, disk, and network metrics for a vSphere VM.
Inputs: name (required), gateway_id.
vsphere_list_hostsC
List all ESXi hosts in the vCenter inventory with CPU, memory, and connection state.
Inputs: cluster, datacenter, gateway_id.
vsphere_list_vmsB
List all VMs in the vCenter inventory. Filter by power_state (all/poweredOn/poweredOff/suspended), datacenter, or cluster.
Inputs: cluster, datacenter, gateway_id, power_state.
vsphere_migrate_vmA
Live-migrate (vMotion) a vSphere VM to another ESXi host. Set dry_run=True to validate without moving.
Inputs: name (required), target_host (required), dry_run, gateway_id.
vsphere_restart_vmB
Restart a vSphere VM. Attempts guest reboot via VMware Tools by default; set force=True for immediate hard reset.
Inputs: name (required), force, gateway_id.
vsphere_start_vmC
Power on a vSphere VM.
Inputs: name (required), gateway_id.
vsphere_stop_vmB
Shut down a vSphere VM. Attempts guest shutdown via VMware Tools by default; set force=True for immediate hard power-off.
Inputs: name (required), force, gateway_id.
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).
Inputs: gateway_id.
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).
Inputs: gateway_id.
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).
Inputs: gateway_id.
xo_list_vmsC
List all VMs on XCP-ng pools managed by Xen Orchestra.
Inputs: gateway_id, power_state.
xo_migrate_vmC
Live-migrate an XCP-ng VM to another host.
Inputs: vm_id (required), target_host_id (required), gateway_id.
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).
Inputs: backup_id (required), target_sr, gateway_id.
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).
Inputs: pool_id (required), gateway_id.
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).
Inputs: job_id (required), gateway_id.
xo_snapshot_vmC
Create a snapshot of an XCP-ng VM.
Inputs: name (required), vm_id (required), gateway_id.
xo_start_vmC
Start a halted XCP-ng VM.
Inputs: vm_id (required), gateway_id.
xo_stop_vmC
Cleanly shutdown a running XCP-ng VM.
Inputs: vm_id (required), gateway_id.
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).
Inputs: gateway_id.
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).
Inputs: esxi_id (required), gateway_id.
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).
Inputs: esxi_id (required), vm_name (required), target_sr, gateway_id, +1 more.
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).
Inputs: task_id (required), gateway_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 117 tools
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.
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.
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.
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
Related MCP Connectors
Protocol-native energy infrastructure orchestration for AI data centers. Provides 46 MCP tools across 8 grid protocols (IEC-61850, DNP3, Modbus, OCPP, OpenADR, IEEE 2030.5, IEC 60870-5-104, ICCP) with 5 core API primitives: connect, dispatch, settle, comply, and intel. Enables AI agents to programmatically interact with substations, grid interfaces, and energy assets for real-time workload-grid coordination.
Autonomous and governed SRE & MLOps control plane for AI agent platforms.
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Related MCP Servers
- AlicenseAqualityBmaintenanceAI Agent Mission Control — 200+ MCP tools across 31 domains. Manage agents, experiments, workflows, crews, skills, tools, credentials, approvals, signals, budgets, marketplace, knowledge bases, chatbots, and more. Self-hosted, open-source (AGPL-3.0). Supports stdio + Streamable HTTP/SSE with OAuth 2.0 auth.3483AGPL 3.0
- AlicenseAqualityBmaintenanceGoverned Kubernetes operations for AI agents with 15 MCP tools, audit logging, policy engine, and safety features.55MIT
- FlicenseNot gradedqualityCmaintenanceProvides real-time monitoring of AI agents, context, usage limits, workflows, files, Git, tests, builds, errors, secrets, and model-economy advice for tools like Claude Code, Codex, and Cursor, with 30 MCP tools for comprehensive observability.1-
- AlicenseBqualityBmaintenanceZero-quota GPU orchestration MCP server — lets AI agents discover, provision, and manage GPU compute across multi-datacenter partner nodes (H100/H200/B200) through a single control plane.479 npmMIT