Soft-delete: move messages to a
AI agents use gmail_move_to_delete to create or update resources in Mariana Google MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mariana Google MCP environment.
Moving messages to a delete folder is a write/modification operation because the messages remain recoverable and the action is reversible (can be moved back or restored from trash). While the word 'delete' appears in the name, the server architecture explicitly implements soft-delete with protections, making this Write rather than Destructive.
From the tool's definition Tool name 'gmail_move_to_delete' and description 'Soft-delete: move messages to a' indicate the action moves (modifies location of) messages rather than permanently deleting them.
Attacks that exploit this kind of access
Soft-delete: move messages to a. It is categorised as a Write tool in the Mariana Google MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mariana Google MCP server in PolicyLayer and add a rule for gmail_move_to_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.
gmail_move_to_delete is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gmail_move_to_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_move_to_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_move_to_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 →