AI agents call snow_ai_classify to retrieve information from Serac without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs content analysis and categorization—a read-only operation that examines input text and returns classification results. It has no side effects on data state, does not execute code or commands, and does not delete or move money. It is purely informational/analytical in nature. Severity is low because misuse would at worst result in incorrect routing decisions, not data loss or unauthorized actions.
From the tool's definition Tool description states it 'Classify a piece of text into one of a caller-supplied list of categories, with a confidence score' and is used for 'routing incoming cases/incidents into queues'.
Attacks that exploit this kind of access
Classify a piece of text into one of a caller-supplied list of categories, with a confidence score. Use for routing incoming cases/incidents into queues or assignment groups by content. It is categorised as a Read tool in the Serac MCP Server, which means it retrieves data without modifying state.
Register the Serac MCP server in PolicyLayer and add a rule for snow_ai_classify: 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_ai_classify 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 snow_ai_classify 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_ai_classify. 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_ai_classify 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_ai_classify 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 →