AI agents use snow_approve_reject to create or update resources in Serac — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Serac environment.
This tool modifies approval request states reversibly within a workflow system. It is Write (not Execute) because it updates data rather than running arbitrary code. It is not Destructive because approval decisions are reversible (can be re-evaluated or overridden by other actors).
From the tool's definition Tool name 'snow_approve_reject' and description 'Approve or reject approval request' indicate state-changing actions that modify workflow approval records in ServiceNow.
Attacks that exploit this kind of access
Approve or reject approval request. It is categorised as a Write tool in the Serac MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Serac MCP server in PolicyLayer and add a rule for snow_approve_reject: 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 Serac. Nothing to install.
snow_approve_reject is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the snow_approve_reject 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 snow_approve_reject. 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.
snow_approve_reject is provided by the Serac MCP server (serac-labs/serac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
snow_approve_reject is one line of Serac's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →