AI agents call mailboxes_status to retrieve information from Imap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a pure read operation—it queries and returns information about mailbox state without side effects. It does not create, modify, delete, execute code, or move funds. The severity is low because exposure of mailbox status metadata poses minimal risk even if misused by an untrusted agent.
From the tool's definition The tool name is 'mailboxes_status' and the description states it 'Get[s] the status of a mailbox'. This is a query operation that retrieves mailbox metadata (such as message counts, unseen message counts, etc.) without modifying data.
Attacks that exploit this kind of access
Get the status of a mailbox. It is categorised as a Read tool in the Imap MCP Server, which means it retrieves data without modifying state.
Register the Imap MCP server in PolicyLayer and add a rule for mailboxes_status: 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 Imap. Nothing to install.
mailboxes_status 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 mailboxes_status 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 mailboxes_status. 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.
mailboxes_status is provided by the Imap MCP server (vivier/imap-mcp-server). 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 →