Delete a draft
AI agents call delete_draft to permanently remove resources in Gmail MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes draft email messages, which cannot be undone. Even though drafts are typically unsent messages, their loss is irreversible and could represent work loss or important composition data. This qualifies as Destructive rather than Write (which is reversible).
From the tool's definition Tool name is 'delete_draft' with description 'Delete a draft'. The verb 'delete' combined with the action of removing a draft email indicates irreversible data deletion.
Attacks that exploit this kind of access
Delete a draft. It is categorised as a Destructive tool in the Gmail MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gmail MCP Server MCP server in PolicyLayer and add a rule for delete_draft: 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 Gmail MCP Server. Nothing to install.
delete_draft 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_draft 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_draft. 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_draft is provided by the Gmail MCP Server MCP server (nk900600/gmail-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 →