AI agents call qf_value_probe 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 probes (queries) field values to retrieve information about possible values in a field. This is a read-only operation that retrieves or inspects data without creating, modifying, deleting, or executing external operations. No destructive or financial actions are possible.
From the tool's definition Tool name 'qf_value_probe' and description 'Probe likely field values for one app field' indicate data querying/retrieval with no modification capability. The phrase 'matched value evidence' suggests inspection and reporting of existing data.
Attacks that exploit this kind of access
Probe likely field values for one app field, with explicit match mode and matched value evidence. 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_value_probe: 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_value_probe 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_value_probe 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_value_probe. 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_value_probe 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 →