run_aggregate_query
Run a grouped aggregate (COUNT, SUM, AVG) query on any table (latest release: /api/now/stats/{table})
This record as markdown: /tools/nowaikit-servicenow-ai-toolkit/run-aggregate-query.md
What run_aggregate_query does on NowAIKit — ServiceNow AI Toolkit
AI agents invoke run_aggregate_query to trigger actions in NowAIKit — ServiceNow AI Toolkit. 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.
Why run_aggregate_query is rated High
This tool executes dynamically constructed queries with argument-dependent behavior, fitting the Execute category. While aggregate functions (COUNT, SUM, AVG) themselves are read-only, the ability to run these queries 'on any table' without explicit restrictions means an AI could be misdirected to query sensitive tables or construct expensive queries that degrade system performance.
From the tool's definition Tool allows execution of arbitrary aggregate queries ('Run a...query on any table') against any table in ServiceNow. The API endpoint pattern /api/now/stats/{table} enables parameterized execution whose effects depend on the table argument provided.
Attacks that exploit this kind of access
The rule that runs run_aggregate_query safely
PolicyLayer is an MCP gateway: it sits between your AI agents and NowAIKit — ServiceNow AI Toolkit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_aggregate_query, this is the rule to start with:
run_aggregate_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.
The button opens the PolicyLayer dashboard: create your workspace, connect NowAIKit — ServiceNow AI Toolkit, apply this rule, and every run_aggregate_query call is checked against it from then on.
Questions about run_aggregate_query
Run a grouped aggregate (COUNT, SUM, AVG) query on any table (latest release: /api/now/stats/{table}). It is categorised as a Execute tool in the NowAIKit — ServiceNow AI Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NowAIKit — ServiceNow AI Toolkit MCP server in PolicyLayer and add a rule for run_aggregate_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 NowAIKit — ServiceNow AI Toolkit. Nothing to install.
run_aggregate_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 run_aggregate_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 run_aggregate_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.
run_aggregate_query is provided by the NowAIKit — ServiceNow AI Toolkit MCP server (nowaikit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on NowAIKit — ServiceNow AI Toolkit, and thousands of servers like it.
Across the catalogue