explain_duplicate
AI agents call explain_duplicate to retrieve information from ServiceNow CMDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to explain or analyze duplicate configuration items already identified in the CMDB. This is a read operation—querying and analyzing existing data without modifying or deleting anything. The absence of 'confirm_', 'create', 'update', or 'delete' in the name, combined with the health-auditing mission of the server, suggests informational output.
From the tool's definition Tool name 'explain_duplicate' paired with 'find_duplicate_cis' suggests analysis/querying of existing duplicate CI data.
Attacks that exploit this kind of access
explain_duplicate. It is categorised as a Read tool in the ServiceNow CMDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ServiceNow CMDB MCP Server MCP server in PolicyLayer and add a rule for explain_duplicate: 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 CMDB MCP Server. Nothing to install.
explain_duplicate 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 explain_duplicate 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 explain_duplicate. 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.
explain_duplicate is provided by the ServiceNow CMDB MCP Server MCP server (ketiil/mcp-cmdb). 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 →