AI agents call delete_gmail_email to permanently remove resources in VaultAssist — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting email is irreversible and destroys data. Although scoped to a single email (lower blast radius than batch operations), it still meets the Destructive category definition. Severity is high because email often contains sensitive information, financial records, or compliance-relevant communications, and deletion cannot be undone.
From the tool's definition Tool name includes 'delete' and description states 'Delete an email by its message ID' — this permanently removes email data without reversal.
Documented attack patterns abuse exactly the kind of access delete_gmail_email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VaultAssist, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_gmail_email:
{
"version": "1",
"default": "deny",
"hide": [
"delete_gmail_email"
]
} delete_gmail_email 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.
Delete an email by its message ID. It is categorised as a Destructive tool in the VaultAssist MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the VaultAssist MCP server in PolicyLayer and add a rule for delete_gmail_email: 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 VaultAssist. Nothing to install.
delete_gmail_email 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_gmail_email 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_gmail_email. 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_gmail_email is provided by the VaultAssist MCP server (3xcaffeine/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VaultAssist, 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.
79 VaultAssist tools catalogued and risk-classified — across an index of 43,000+ MCP servers.