Move one or more Gmail messages to trash
AI agents use trash_gmail to create or update resources in Google Connections — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Connections environment.
This is a Write operation because it modifies data state reversibly rather than permanently deleting it. Moving to trash is a soft delete that preserves the ability to restore messages, distinguishing it from permanent deletion.
From the tool's definition Tool name 'trash_gmail' and description 'Move one or more Gmail messages to trash' indicates the action is reversible—messages moved to trash can be recovered from the trash folder within Gmail's retention period.
Attacks that exploit this kind of access
Move one or more Gmail messages to trash. It is categorised as a Write tool in the Google Connections MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Connections MCP server in PolicyLayer and add a rule for trash_gmail: 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 Google Connections. Nothing to install.
trash_gmail 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_gmail 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_gmail. 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_gmail is provided by the Google Connections MCP server (michaelzrork/google-connections-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 →