AI agents use qf.records.mutate to create or update resources in Qingflow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qingflow environment.
This tool creates or modifies records reversibly. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). While high severity due to potential data modification impact in a business workflow system, it remains in the Write category as the operations described are not irreversible.
From the tool's definition Tool description states 'Canonical write entry for create/update operations.' The name 'mutate' combined with the descriptor indicates reversible data modification without deletion.
Attacks that exploit this kind of access
Canonical write entry for create/update operations. It is categorised as a Write tool in the Qingflow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qingflow MCP server in PolicyLayer and add a rule for qf.records.mutate: 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.records.mutate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the qf.records.mutate 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.records.mutate. 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.records.mutate 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 →