Get the XML export payload for an Update Set (as used in migration). [Scripting]
AI agents call export_update_set to retrieve information from ServiceNow-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and returns an XML export of an Update Set, which is a read operation. However, severity is medium because Update Sets can contain sensitive configuration, scripts, and customizations. The [Scripting] tag suggests the exported payload may include executable code, but the tool itself only retrieves/exports it without executing anything.
From the tool's definition 'Get the XML export payload for an Update Set (as used in migration)' - this retrieves/exports data rather than modifying it
Attacks that exploit this kind of access
Get the XML export payload for an Update Set (as used in migration). [Scripting]. It is categorised as a Read tool in the ServiceNow-MCP MCP Server, which means it retrieves data without modifying state.
Register the ServiceNow- MCP server in PolicyLayer and add a rule for export_update_set: 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 ServiceNow-MCP. Nothing to install.
export_update_set 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 export_update_set 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 export_update_set. 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.
export_update_set is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →