Get full details of a single ServiceNow incident by number (e.g., INC0012345) or sys_id. Args: - identifier (string): Incident number (INC...) or sys_id - response_format: Output format Returns: Complete incident details including description, work notes, and all fields
AI agents call servicenow_get_incident to retrieve information from Servicenow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries incident data by identifier. It performs a read-only operation with no ability to modify, delete, or execute actions. The blast radius of misuse is limited to unauthorized information disclosure about a specific incident, which is low severity in a typical ServiceNow environment.
From the tool's definition Tool name 'servicenow_get_incident' and description 'Get full details of a single ServiceNow incident' with no modification, deletion, or execution capability. Returns 'Complete incident details' without side effects.
Attacks that exploit this kind of access
Get full details of a single ServiceNow incident by number (e.g., INC0012345) or sys_id. Args: - identifier (string): Incident number (INC...) or sys_id - response_format: Output format Returns: Complete incident details including description, work notes, and all fields. It is categorised as a Read tool in the Servicenow MCP Server, which means it retrieves data without modifying state.
Register the Servicenow MCP server in PolicyLayer and add a rule for servicenow_get_incident: 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. Nothing to install.
servicenow_get_incident 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 servicenow_get_incident 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 servicenow_get_incident. 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.
servicenow_get_incident is provided by the Servicenow MCP server (kylburns89/servicenow-mcp-server). 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 →