AI agents invoke perform_query to trigger actions in ServiceNow MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The name 'perform_query' suggests executing a query against ServiceNow. On a server that also includes natural_language_update and update operations, a generic 'perform_query' could execute arbitrary read or write operations. With no description available, confidence is reduced, but the 'perform' prefix implies active execution rather than passive retrieval.
From the tool's definition Tool name 'perform_query' on a server that manipulates ServiceNow data; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access perform_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ServiceNow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for perform_query:
{
"version": "1",
"default": "deny",
"tools": {
"perform_query": {
"limits": [
{
"counter": "perform_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}perform_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
perform_query. It is categorised as a Execute tool in the ServiceNow MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ServiceNow MCP Server MCP server in PolicyLayer and add a rule for perform_query: 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 Server. Nothing to install.
perform_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the perform_query 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 perform_query. 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.
perform_query is provided by the ServiceNow MCP Server MCP server (michaelbuckner/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ServiceNow MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 ServiceNow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.