Rule-based classifier into protected_finance/protected_travel/security/support_case (never deleted) vs marketing/routine_notification (cleanup candidates) vs unknown. Returns a plan by default (read-only). DESTRUCTIVE when confirm=true: deletes the marketing/routine_notification candidates (moved...
AI agents call cleanup to permanently remove resources in MCP Email Service — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
When confirm=true, the tool irreversibly deletes emails, and with permanent=true those deletions bypass trash entirely. The bulk, rule-based nature means an AI agent could inadvertently delete large volumes of email across multiple accounts. Although a read-only planning mode exists by default, the destructive path is the primary risk and dominates classification per severity rules.
From the tool's definition DESTRUCTIVE when confirm=true: deletes the marketing/routine_notification candidates (moved to trash unless permanent=true)
Documented attack patterns abuse exactly the kind of access cleanup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Email Service, and nothing reaches the server without passing your rules. This is the rule we recommend for cleanup:
{
"version": "1",
"default": "deny",
"hide": [
"cleanup"
]
}cleanup 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.
Rule-based classifier into protected_finance/protected_travel/security/support_case (never deleted) vs marketing/routine_notification (cleanup candidates) vs unknown. Returns a plan by default (read-only). DESTRUCTIVE when confirm=true: deletes the marketing/routine_notification candidates (moved to trash unless permanent=true). It is categorised as a Destructive tool in the MCP Email Service MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Email Service MCP server in PolicyLayer and add a rule for cleanup: 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 Email Service. Nothing to install.
cleanup 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 cleanup 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 cleanup. 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.
cleanup is provided by the MCP Email Service MCP server (leeguooooo/mailbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Email Service, 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.
16 MCP Email Service tools catalogued and risk-classified — across an index of 43,000+ MCP servers.