trash-email
AI agents use trash-email to create or update resources in Gmail Plugin MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail Plugin MCP Server environment.
Trashing an email modifies the email's state (moves it to trash folder) but is reversible—users can restore from trash. This makes it Write rather than Destructive. The blast radius is medium: an AI agent trashing emails without authorization could disrupt user workflows, but recovery is possible. This is less severe than permanent deletion (which would be Destructive) or financial operations.
From the tool's definition Tool name 'trash-email' indicates moving an email to trash, which modifies email state. Server description lists 'trash' as a managed operation. No description provided for the tool itself, limiting confidence slightly.
Attacks that exploit this kind of access
trash-email. It is categorised as a Write tool in the Gmail Plugin MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail Plugin MCP Server MCP server in PolicyLayer and add a rule for trash-email: 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 Plugin MCP Server. Nothing to install.
trash-email 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 trash-email 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 trash-email. 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.
trash-email is provided by the Gmail Plugin MCP Server MCP server (sanchisingh01/mcp-server---gmail-plugin-for-claude-desktop). 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 →