# ml_virtual_agent_nlu

Analyse Virtual Agent NLU performance — conversation completion rates and fallback metrics

Agent View of the PolicyLayer registry record for `ml_virtual_agent_nlu`. HTML page: https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/ml-virtual-agent-nlu

## Facts

- Tool: `ml_virtual_agent_nlu`
- Server: NowAIKit — ServiceNow AI Toolkit (`nowaikit`) — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit.md
- Install: `npx -y nowaikit`
- Homepage: https://github.com/aartiq/nowaikit
- Risk category: Read (Low risk)
- Registry record: grade F, identity verified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ml_virtual_agent_nlu",
    "arguments": {}
  }
}
```

## Why ml_virtual_agent_nlu is rated Low

This tool analyzes and retrieves performance metrics from a Virtual Agent NLU system. The verb 'Analyse' and the specific metrics mentioned (completion rates, fallback metrics) indicate read-only querying of existing data. There is no evidence of creating, modifying, deleting data or executing external operations. The blast radius of misuse is limited to potential exposure of performance analytics data.

From the tool's own definition: "Tool name 'ml_virtual_agent_nlu' and description 'Analyse Virtual Agent NLU performance — conversation completion rates and fallback metrics' indicates data retrieval and analysis of performance metrics with no modification or execution of external operations."

## Use case

AI agents call ml_virtual_agent_nlu to retrieve information from NowAIKit — ServiceNow AI Toolkit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches NowAIKit — ServiceNow AI Toolkit:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "ml_virtual_agent_nlu": {}
  }
}
```

## Other tools on NowAIKit — ServiceNow AI Toolkit (409)

- `cmdb_reconcile` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/cmdb-reconcile.md
- `delete_attachment` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/delete-attachment.md
- `delete_record` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/delete-record.md
- `delete_system_property` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/delete-system-property.md
- `delete_uib_page` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/delete-uib-page.md
- `remove_user_from_group` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/remove-user-from-group.md
- `rollback_changes` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/rollback-changes.md
- `rollback_deployment` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/rollback-deployment.md
- `visualize_aggregate` — Destructive — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/visualize-aggregate.md
- `batch_request` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/batch-request.md
- `categorize_incident` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/categorize-incident.md
- `commit_changeset` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/commit-changeset.md
- `create_business_rule` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/create-business-rule.md
- `create_flow_action` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/create-flow-action.md
- `create_scheduled_job` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/create-scheduled-job.md
- `execute_background_script` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/execute-background-script.md
- `execute_playbook` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/execute-playbook.md
- `execute_script` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/execute-script.md
- `fire_event` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/fire-event.md
- `fluent_build` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/fluent-build.md
- `fluent_explain` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/fluent-explain.md
- `fluent_init` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/fluent-init.md
- `fluent_validate` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/fluent-validate.md
- `ml_detect_anomalies` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/ml-detect-anomalies.md
- `ml_train_anomaly_detector` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/ml-train-anomaly-detector.md
- `ml_train_change_risk` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/ml-train-change-risk.md
- `ml_train_incident_classifier` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/ml-train-incident-classifier.md
- `publish_changeset` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/publish-changeset.md
- `run_aggregate_query` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/run-aggregate-query.md
- `run_atf_suite` — Execute — https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit/run-atf-suite.md
- …and 379 more: https://policylayer.com/tools/nowaikit-servicenow-ai-toolkit.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=nowaikit-servicenow-ai-toolkit · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/nowaikit-servicenow-ai-toolkit