AI agents call qf.query.plan 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.
qf_query_plan is a query planning and validation tool that analyzes and normalizes query inputs without executing them or modifying data. It returns estimates and readiness assessments, which are read-only metadata operations. Even though it may interact with schema or internal representations, it has no side effects on actual data and is subordinate to the actual qf_query execution tool.
From the tool's definition Tool description states it performs 'Preflight canonical query DSL, normalize loose inputs, translate into internal tools and estimate whether the query is ready' — these are preparatory, non-mutative analysis operations.
Attacks that exploit this kind of access
Preflight canonical query DSL, normalize loose inputs, translate into internal tools and estimate whether the query is ready for a final conclusion. 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.plan: 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.plan 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.plan 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.plan. 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.plan 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 →