AI agents call servicenow_data_classification to retrieve information from Servicenow Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates a data classification function, which typically retrieves and organizes existing data without side effects. With an empty description, confidence is reduced, but the absence of action verbs like 'create', 'delete', 'execute', or 'change' and the Read-oriented naming pattern of similar ServiceNow tools (aggregate, attachment) suggest this is informational.
From the tool's definition Tool name 'servicenow_data_classification' suggests classification or categorization operations. Description is empty, limiting direct evidence.
Documented attack patterns abuse exactly the kind of access servicenow_data_classification gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Servicenow Api, and nothing reaches the server without passing your rules. This is the rule we recommend for servicenow_data_classification:
{
"version": "1",
"default": "deny",
"tools": {
"servicenow_data_classification": {}
}
}servicenow_data_classification is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
servicenow_data_classification. It is categorised as a Read tool in the Servicenow Api MCP Server, which means it retrieves data without modifying state.
Register the Servicenow Api MCP server in PolicyLayer and add a rule for servicenow_data_classification: 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 Servicenow Api. Nothing to install.
servicenow_data_classification 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 servicenow_data_classification 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 servicenow_data_classification. 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.
servicenow_data_classification is provided by the Servicenow Api MCP server (knuckles-team/servicenow-api). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Servicenow Api, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Servicenow Api tools catalogued and risk-classified — across an index of 43,000+ MCP servers.