Search emails in a specific mailbox (includes content search)
AI agents call mail_search_mailbox to retrieve information from MCP Apple Mail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation across email contents and metadata within a specified mailbox. It retrieves matching results but does not create, modify, delete, or execute code. The search capability, while potentially exposing sensitive email content to an AI agent, is fundamentally a read operation.
From the tool's definition Tool name 'mail_search_mailbox' and description 'Search emails in a specific mailbox (includes content search)' indicate a query operation that retrieves and filters email data without modification.
Attacks that exploit this kind of access
Search emails in a specific mailbox (includes content search). It is categorised as a Read tool in the MCP Apple Mail MCP Server, which means it retrieves data without modifying state.
Register the MCP Apple Mail MCP server in PolicyLayer and add a rule for mail_search_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 MCP Apple Mail. Nothing to install.
mail_search_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 mail_search_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 mail_search_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.
mail_search_mailbox is provided by the MCP Apple Mail MCP server (lionsr/mcp-apple). 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 →