# create_now_assist_skill

Create a Now Assist skill definition (requires NOW_ASSIST_ENABLED + WRITE_ENABLED)

Agent View of the PolicyLayer registry record for `create_now_assist_skill`. HTML page: https://policylayer.com/tools/servicenow-mcp-server/create-now-assist-skill

## Facts

- Tool: `create_now_assist_skill`
- Server: ServiceNow MCP Server (`@aartiq/servicenow-mcp`) — https://policylayer.com/tools/servicenow-mcp-server.md
- Install: `npx -y @aartiq/servicenow-mcp`
- Homepage: https://github.com/aartiq/servicenow-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity verified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why create_now_assist_skill is rated Medium

This tool creates a new resource (a Now Assist skill definition) in ServiceNow. Creation operations are reversible and fall into the Write category. Severity is medium because creating unwanted skills could complicate AI automation workflows and potentially expose unintended capabilities, but the impact is scoped to skill definitions and doesn't involve deletion, financial impact, or uncontrolled code execution.

From the tool's own definition: "The tool description explicitly states 'Create a Now Assist skill definition', which is a create operation that modifies ServiceNow's configuration by adding a new skill resource. The requirement flags 'WRITE_ENABLED' confirm this is a write capability."

## Use case

AI agents use create_now_assist_skill to create or update resources in ServiceNow MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ServiceNow MCP Server environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches ServiceNow MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_now_assist_skill": {
      "limits": [
        {
          "counter": "create_now_assist_skill_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on ServiceNow MCP Server (414)

- `cmdb_reconcile` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/cmdb-reconcile.md
- `delete_attachment` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/delete-attachment.md
- `delete_record` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/delete-record.md
- `delete_system_property` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/delete-system-property.md
- `delete_uib_page` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/delete-uib-page.md
- `remove_user_from_group` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/remove-user-from-group.md
- `rollback_changes` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/rollback-changes.md
- `rollback_deployment` — Destructive — https://policylayer.com/tools/servicenow-mcp-server/rollback-deployment.md
- `batch_request` — Execute — https://policylayer.com/tools/servicenow-mcp-server/batch-request.md
- `categorize_incident` — Execute — https://policylayer.com/tools/servicenow-mcp-server/categorize-incident.md
- `commit_changeset` — Execute — https://policylayer.com/tools/servicenow-mcp-server/commit-changeset.md
- `create_business_rule` — Execute — https://policylayer.com/tools/servicenow-mcp-server/create-business-rule.md
- `create_flow_action` — Execute — https://policylayer.com/tools/servicenow-mcp-server/create-flow-action.md
- `create_scheduled_job` — Execute — https://policylayer.com/tools/servicenow-mcp-server/create-scheduled-job.md
- `create_script_include` — Execute — https://policylayer.com/tools/servicenow-mcp-server/create-script-include.md
- `create_ui_action` — Execute — https://policylayer.com/tools/servicenow-mcp-server/create-ui-action.md
- `execute_background_script` — Execute — https://policylayer.com/tools/servicenow-mcp-server/execute-background-script.md
- `execute_playbook` — Execute — https://policylayer.com/tools/servicenow-mcp-server/execute-playbook.md
- `execute_script` — Execute — https://policylayer.com/tools/servicenow-mcp-server/execute-script.md
- `fire_event` — Execute — https://policylayer.com/tools/servicenow-mcp-server/fire-event.md
- `fluent_build` — Execute — https://policylayer.com/tools/servicenow-mcp-server/fluent-build.md
- `fluent_explain` — Execute — https://policylayer.com/tools/servicenow-mcp-server/fluent-explain.md
- `fluent_init` — Execute — https://policylayer.com/tools/servicenow-mcp-server/fluent-init.md
- `fluent_validate` — Execute — https://policylayer.com/tools/servicenow-mcp-server/fluent-validate.md
- `ml_detect_anomalies` — Execute — https://policylayer.com/tools/servicenow-mcp-server/ml-detect-anomalies.md
- `ml_train_anomaly_detector` — Execute — https://policylayer.com/tools/servicenow-mcp-server/ml-train-anomaly-detector.md
- `ml_train_change_risk` — Execute — https://policylayer.com/tools/servicenow-mcp-server/ml-train-change-risk.md
- `ml_train_incident_classifier` — Execute — https://policylayer.com/tools/servicenow-mcp-server/ml-train-incident-classifier.md
- `publish_changeset` — Execute — https://policylayer.com/tools/servicenow-mcp-server/publish-changeset.md
- `run_aggregate_query` — Execute — https://policylayer.com/tools/servicenow-mcp-server/run-aggregate-query.md
- …and 384 more: https://policylayer.com/tools/servicenow-mcp-server.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=servicenow-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/servicenow-mcp-server