Permanently delete a draft. Idempotent on the outcome (already-deleted drafts return 404 from Gmail).
AI agents call gmail_draft_delete to permanently remove resources in Mcp Gmail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes draft messages from Gmail. Although drafts are typically lower-stakes than sent messages, permanent deletion without undo capability falls squarely into the Destructive category.
From the tool's definition Tool description explicitly states 'Permanently delete a draft' — this is an irreversible deletion operation. The term 'Permanently' confirms data cannot be recovered.
Attacks that exploit this kind of access
Permanently delete a draft. Idempotent on the outcome (already-deleted drafts return 404 from Gmail). It is categorised as a Destructive tool in the Mcp Gmail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for gmail_draft_delete: 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 Gmail. Nothing to install.
gmail_draft_delete 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_draft_delete 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_draft_delete. 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_draft_delete is provided by the Mcp Gmail MCP server (knowledgeislands/mcp-gmail). 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 →