Search ServiceNow using plain English (experimental)
AI agents call natural_language_search 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 retrieves or queries data from ServiceNow using natural language input. It has no side effects—it does not create, modify, delete, or execute operations. Even though it interfaces with a large service management system, the blast radius of misuse is limited to information disclosure.
From the tool's definition Tool name is 'natural_language_search' and description states 'Search ServiceNow using plain English'. The word 'search' and the function of querying data without modification indicate retrieval-only behavior.
Attacks that exploit this kind of access
Search ServiceNow using plain English (experimental). 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 natural_language_search: 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.
natural_language_search 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 natural_language_search 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 natural_language_search. 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.
natural_language_search 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 →