AI agents call qf.query.aggregate to retrieve information from Qingflow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs aggregation queries to compute metrics (sum, count, average, etc.) over records and returns results. This is a read-only operation that queries and analyzes data without side effects. The mention of 'query handle resources' suggests result set management typical of read operations. No data modification, deletion, or execution of arbitrary code is indicated.
From the tool's definition Tool name 'aggregate' combined with description 'return metrics_by_column' indicates data retrieval and computation of summary statistics. No modification, deletion, or code execution is described.
Attacks that exploit this kind of access
Aggregate records through the canonical DSL and return metrics_by_column plus query handle resources. It is categorised as a Read tool in the Qingflow MCP Server, which means it retrieves data without modifying state.
Register the Qingflow MCP server in PolicyLayer and add a rule for qf.query.aggregate: 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 Qingflow. Nothing to install.
qf.query.aggregate 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 qf.query.aggregate 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 qf.query.aggregate. 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.
qf.query.aggregate is provided by the Qingflow MCP server (qingflow-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 →