Delete a draft. Requires gmail.compose scope.
AI agents call gmail.deleteDraft 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 removes data (a draft email) without possibility of undo. While the blast radius is limited to a single draft (not production data or financial systems), deletion is inherently destructive. Severity is medium rather than high because the impact scope is typically confined to user-created draft content, not critical business data or system integrity.
From the tool's definition Tool name explicitly includes 'delete' and description states 'Delete a draft.' The action is irreversible—once deleted, the draft cannot be recovered.
Attacks that exploit this kind of access
Delete a draft. Requires gmail.compose scope. 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 gmail.deleteDraft: 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.
gmail.deleteDraft 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 gmail.deleteDraft 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 gmail.deleteDraft. 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.
gmail.deleteDraft is provided by the Gmail MCP Server MCP server (shcallaway/gmail-mcp-server). 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 →