AI agents use snow_callback_handler 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.
The tool creates a new callback handler resource, which is a write operation (creating/registering a handler). It doesn't appear to delete or overwrite data irreversibly, nor does it execute arbitrary code directly or move money. Severity is medium because misconfigured async callback handlers in a ServiceNow environment could cause unintended side effects or intercept/redirect async operation results.
From the tool's definition "Create callback handler for async operations"
Attacks that exploit this kind of access
Create callback handler for async operations. 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_callback_handler: 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_callback_handler 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_callback_handler 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_callback_handler. 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_callback_handler 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_callback_handler 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 →