Remove a bounced address from the bounce suppression list via DELETE /suppression/bounces/{email}. Call this after the recipient confirms the underlying issue (e.g. mailbox full) is resolved.
AI agents call delete_bounce 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 permanently removes data (a bounced address entry) from a suppression list without the ability to undo the action. While the use case is legitimate (after confirming the issue is resolved), the underlying operation is destructive—it irreversibly deletes a record.
From the tool's definition Tool name contains 'delete'; description explicitly states 'Remove a bounced address' via DELETE method, indicating irreversible removal from the bounce suppression list.
Documented attack patterns abuse exactly the kind of access delete_bounce 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_bounce:
{
"version": "1",
"default": "deny",
"hide": [
"delete_bounce"
]
} delete_bounce 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.
Remove a bounced address from the bounce suppression list via DELETE /suppression/bounces/{email}. Call this after the recipient confirms the underlying issue (e.g. mailbox full) is resolved. 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_bounce: 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_bounce 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_bounce 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_bounce. 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_bounce 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.