Delete a Gmail label by name or ID. Cannot delete system labels. Requires confirmation.
AI agents call gmail_delete_label 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.
Although the tool requires confirmation and cannot delete system labels (safety constraints), deleting a label is an irreversible operation that destroys user-created organizational metadata. This qualifies as Destructive rather than Write since the action cannot be undone.
From the tool's definition Tool explicitly performs 'Delete a Gmail label' which is an irreversible data deletion action. Labels are organizational data structures that cannot be recovered once deleted.
Attacks that exploit this kind of access
Delete a Gmail label by name or ID. Cannot delete system labels. Requires confirmation. 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_delete_label: 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_delete_label 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_delete_label 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_delete_label. 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_delete_label is provided by the Gmail MCP Server MCP server (murphy360/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 →