Create, edit, verify, and delete one dummy contact. Requires confirm=true.
AI agents call test_roundtrip to permanently remove resources in Apple Contacts MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Even though the contact created is a dummy/test contact, the tool performs a deletion as a final step, which is irreversible. The most severe action in this multi-step operation is the delete, placing it in the Destructive category. The require confirm=true flag indicates the authors themselves recognize the risk.
From the tool's definition 'Create, edit, verify, and delete one dummy contact' — the tool explicitly deletes a contact as part of its operation, which is irreversible.
Attacks that exploit this kind of access
Create, edit, verify, and delete one dummy contact. Requires confirm=true. It is categorised as a Destructive tool in the Apple Contacts MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Apple Contacts MCP server in PolicyLayer and add a rule for test_roundtrip: 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 Apple Contacts MCP. Nothing to install.
test_roundtrip 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 test_roundtrip 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 test_roundtrip. 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.
test_roundtrip is provided by the Apple Contacts MCP server (lu-wo/apple-contacts-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 →