Soft-delete an applicant. Onfido retains the record for 30 days before permanent deletion; during that window it can be restored via the dashboard.
AI agents call delete_applicant to permanently remove resources in Mcp Ap2 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool meets the Destructive category because it deletes data that cannot be undone after the 30-day retention period expires. Even though soft-delete allows temporary recovery, the primary action is removal of applicant records, which in an identity verification/payment protocol context (AP2 - Agent-to-Agent Payment Protocol) represents sensitive personal or verification data.
From the tool's definition The tool performs a 'Soft-delete' operation on an applicant record. While technically recoverable within a 30-day window, it removes data from active use and permanently deletes it after 30 days.
Documented attack patterns abuse exactly the kind of access delete_applicant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_applicant:
{
"version": "1",
"default": "deny",
"hide": [
"delete_applicant"
]
} delete_applicant disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Soft-delete an applicant. Onfido retains the record for 30 days before permanent deletion; during that window it can be restored via the dashboard. It is categorised as a Destructive tool in the Mcp Ap2 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for delete_applicant: 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 Mcp Ap2. Nothing to install.
delete_applicant 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_applicant 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_applicant. 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_applicant is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.