Get AI-powered resolution suggestion for an incident based on similar past incidents
AI agents call suggest_resolution 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.
This tool performs a read-only operation that searches historical incident data and returns AI-generated suggestions. It has no side effects on ServiceNow data or external systems. While the output (a suggestion) may inform human decision-making, the tool itself neither modifies data, executes commands, nor commits any changes.
From the tool's definition Tool description: 'Get AI-powered resolution suggestion for an incident based on similar past incidents'. The verb 'Get' and 'suggestion' indicate data retrieval only.
Attacks that exploit this kind of access
Get AI-powered resolution suggestion for an incident based on similar past incidents. 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 suggest_resolution: 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.
suggest_resolution 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 suggest_resolution 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 suggest_resolution. 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.
suggest_resolution 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 →