Request a physical action on a package at the facility. Actions include forwarding to another address, shredding, scanning documents, holding for pickup, disposing, returning to sender, photographing, opening and scanning contents, or recording a video. Some actions (shred, dispose) are irreversi...
Part of the Mailbox server.
Free to start. No card required.
AI agents may call request_action to permanently remove or destroy resources in Mailbox. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call request_action in a loop, permanently destroying resources in Mailbox. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"request_action"
]
}See the full Mailbox policy for all 29 tools.
These attack patterns abuse exactly the kind of access request_action gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Request a physical action on a package at the facility. Actions include forwarding to another address, shredding, scanning documents, holding for pickup, disposing, returning to sender, photographing, opening and scanning contents, or recording a video. Some actions (shred, dispose) are irreversible.. It is categorised as a Destructive tool in the Mailbox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mailbox MCP server in PolicyLayer and add a rule for request_action: 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 Mailbox. Nothing to install.
request_action 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 request_action 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 request_action. 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.
request_action is provided by the Mailbox MCP server (https://mailbox.bot/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 Mailbox tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.