natural_language_update · ServiceNow- MCP: Risk & Policy

WHAT IT DOES

What natural_language_update does on ServiceNow-MCP

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

WHY IT NEEDS A POLICY

Why natural_language_update needs a policy

This tool modifies existing ServiceNow records through natural language interpretation. While it creates/updates data reversibly (satisfying Write category), the severity is elevated to 'high' because: (1) natural language interpretation of update intent introduces ambiguity risk—an AI agent could misinterpret user intent and corrupt unintended fields; (2) ServiceNow records often contain critical business data…

From the tool's definition Tool name 'natural_language_update' and description states it 'Update[s] a record' with natural language input. The description explicitly requires 'WRITE_ENABLED=true', confirming write capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

natural_language_update Rate-limited

natural_language_update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "natural_language_update": {
      "limits": [
        {
          "counter": "natural_language_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ServiceNow-MCP, so you can run agents against it safely.

FAQ

Questions about natural_language_update

What does the natural_language_update tool do? +

Update a record using natural language (experimental, requires WRITE_ENABLED=true). It is categorised as a Write tool in the ServiceNow-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on natural_language_update? +

Register the ServiceNow- MCP server in PolicyLayer and add a rule for natural_language_update: 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-MCP. Nothing to install.

What risk level is natural_language_update? +

natural_language_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit natural_language_update? +

Yes. Add a rate_limit block to the natural_language_update 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.

How do I block natural_language_update completely? +

Set action: deny in the PolicyLayer policy for natural_language_update. 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.

What MCP server provides natural_language_update? +

natural_language_update is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.