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 performs validation and estimation without executing queries or modifying state. It reads configuration/schema (to resolve mappings and estimate limits) but does not retrieve, create, modify, or delete data. This is a Read category tool with low blast radius: misuse would cause validation errors or estimation inaccuracies, not data loss or unauthorized operations.
From the tool's definition Tool name and description indicate preflight validation: 'normalize inputs, validate required fields, resolve mappings and estimate scan limits before execution.' These are inspection and planning activities with no data retrieval, modification, or…
Attacks that exploit this kind of access
Preflight query arguments: normalize inputs, validate required fields, resolve mappings and estimate scan limits before execution. 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 →