AI agents invoke snow_run_discovery 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.
This is Execute rather than Write because it triggers an asynchronous external system operation (discovery scan) whose outcome is not simply a reversible data creation but rather an active probe and enumeration of infrastructure. An agent with misuse capability could target sensitive network ranges, internal servers, or critical infrastructure segments, initiating unauthorized reconnaissance.
From the tool's definition The tool "Queue[s] a CMDB discovery scan" and "scan runs asynchronously". This triggers an external operation (ServiceNow discovery engine) whose effects depend on arguments (target IP/range, MID Server selection).
Attacks that exploit this kind of access
Queue a CMDB discovery scan against a discovery schedule, optionally narrowed to a target IP/range and a specific MID Server. Creates a discovery_schedule_item; the scan runs asynchronously. 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_run_discovery: 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_run_discovery 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_run_discovery 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_run_discovery. 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_run_discovery 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_run_discovery 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 →