categorize_incident
Suggest category, assignment group, and priority for an incident by analysing similar resolved incidents (Table API). Predictive Intelligence has no public REST prediction endpoint; for model-based scoring run PI on-record and read the predicted field.
This record as markdown: /tools/nowaikit-servicenow-ai-toolkit/categorize-incident.md
What categorize_incident does on NowAIKit — ServiceNow AI Toolkit
AI agents call categorize_incident 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.
Why categorize_incident is rated Low
The tool performs analysis of historical incident data to generate predictions/suggestions. It explicitly notes that for model-based scoring you must 'run PI on-record and read the predicted field,' confirming the tool itself only reads and suggests rather than modifying any records. No write, execute, or destructive operations are described.
From the tool's definition 'Suggest category, assignment group, and priority for an incident by analysing similar resolved incidents (Table API)' — the tool reads/queries existing incident data to produce suggestions, with no indication of writing or modifying records.
Attacks that exploit this kind of access
The rule that runs categorize_incident safely
PolicyLayer is an MCP gateway: it sits between your AI agents and NowAIKit — ServiceNow AI Toolkit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For categorize_incident, this is the rule to start with:
categorize_incident is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect NowAIKit — ServiceNow AI Toolkit, apply this rule, and every categorize_incident call is checked against it from then on.
Questions about categorize_incident
Suggest category, assignment group, and priority for an incident by analysing similar resolved incidents (Table API). Predictive Intelligence has no public REST prediction endpoint; for model-based scoring run PI on-record and read the predicted field. It is categorised as a Read tool in the NowAIKit — ServiceNow AI Toolkit MCP Server, which means it retrieves data without modifying state.
Register the NowAIKit — ServiceNow AI Toolkit MCP server in PolicyLayer and add a rule for categorize_incident: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches NowAIKit — ServiceNow AI Toolkit. Nothing to install.
categorize_incident is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the categorize_incident rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for categorize_incident. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
categorize_incident is provided by the NowAIKit — ServiceNow AI Toolkit MCP server (nowaikit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on NowAIKit — ServiceNow AI Toolkit, and thousands of servers like it.
This server
Across the catalogue