Watch for changes to the user
AI agents call watch_mailbox to retrieve information from Gmail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The watch operation is fundamentally a read/monitoring function that observes mailbox changes and reports them back. While it has moderate severity due to the sensitivity of email data and potential for monitoring emails in real-time, it does not create, modify, delete, or execute operations.
From the tool's definition Tool name 'watch_mailbox' and description 'Watch for changes to the user' indicate monitoring/observation of mailbox state changes. This is a read operation that retrieves change notifications without modifying data.
Attacks that exploit this kind of access
Watch for changes to the user. It is categorised as a Read tool in the Gmail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gmail MCP Server MCP server in PolicyLayer and add a rule for watch_mailbox: 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 MCP Server. Nothing to install.
watch_mailbox is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the watch_mailbox 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 watch_mailbox. 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.
watch_mailbox is provided by the Gmail MCP Server MCP server (nk900600/gmail-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 →