AI agents use gmail_recover_from_trash to create or update resources in Mcp Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gmail environment.
The name suggests recovering (restoring) emails from trash, which is a reversible write operation that moves messages back to their original location. This is not destructive (it undoes a deletion rather than causing one), not a pure read, and not financial. Confidence is reduced because the description is empty, leaving some ambiguity about exact behavior.
From the tool's definition Tool name: 'gmail_recover_from_trash' — implies restoring/moving emails out of trash back to inbox or original folder.
Attacks that exploit this kind of access
gmail_recover_from_trash. It is categorised as a Write tool in the Mcp Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for gmail_recover_from_trash: 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_recover_from_trash 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_recover_from_trash 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_recover_from_trash. 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_recover_from_trash is provided by the Mcp Gmail MCP server (@monsoft/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 →