delete_toll_qa_pair
AI agents call delete_toll_qa_pair to permanently remove resources in Plurity — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes QA pair data, which cannot be undone. This is an irreversible modification of state. Although the blast radius is limited to QA pair records (not system-wide or financial), deletion of structured data warrants 'high' severity. Destructive is the only applicable category here.
From the tool's definition Tool name 'delete_toll_qa_pair' explicitly indicates irreversible deletion of data (QA pair records). The 'delete_' prefix is a strong signal of a Destructive operation.
Attacks that exploit this kind of access
delete_toll_qa_pair. It is categorised as a Destructive tool in the Plurity MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Plurity MCP server in PolicyLayer and add a rule for delete_toll_qa_pair: 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 Plurity. Nothing to install.
delete_toll_qa_pair is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_toll_qa_pair 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 delete_toll_qa_pair. 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.
delete_toll_qa_pair is provided by the Plurity MCP server (plurity-ai/plurity-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 →