AI agents invoke snow_ml_predict to trigger actions in Serac. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Running an ML prediction invokes an external computational process (model inference) that produces outputs potentially used in automated decision-making within ServiceNow. While it doesn't directly delete data or move money, it executes a model whose predictions could drive downstream actions (routing, approvals, risk scoring).
From the tool's definition 'Make ML prediction using trained model' — triggers execution of a trained machine learning model against input data
Attacks that exploit this kind of access
Make ML prediction using trained model. It is categorised as a Execute tool in the Serac MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Serac MCP server in PolicyLayer and add a rule for snow_ml_predict: 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_ml_predict is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the snow_ml_predict 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_ml_predict. 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_ml_predict 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_ml_predict 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 →