Soft-delete: prepend
AI agents call calendar_flag_delete to permanently remove resources in Mariana Google MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs a delete operation on calendar entries. Although described as a 'soft-delete' (which implies some reversibility via prepending a marker rather than permanent removal), the intent and primary action is deletion. The server description notes 'mandatory manual confirmation for destructive actions' and 'soft-delete protections', suggesting this is treated as a destructive action by the server itself.
From the tool's definition Tool name contains 'delete'; description mentions 'Soft-delete: prepend'
Attacks that exploit this kind of access
Soft-delete: prepend. It is categorised as a Destructive tool in the Mariana Google MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mariana Google MCP server in PolicyLayer and add a rule for calendar_flag_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 Mariana Google MCP. Nothing to install.
calendar_flag_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 calendar_flag_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 calendar_flag_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.
calendar_flag_delete is provided by the Mariana Google MCP server (marianasmall/mariana-google-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 →