List unread messages outside the inbox that may need attention.
AI agents call missed_mail to retrieve information from Personal Mail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing unread mail data. It performs a read-only operation that returns information to the user without creating, modifying, deleting, or executing any actions. The blast radius of misuse is minimal—an AI agent could only access metadata about unread messages outside the inbox, which represents low risk.
From the tool's definition Tool name and description indicate it 'List unread messages' — a query operation with no modification, deletion, or execution capability. The description explicitly states it retrieves data ('List...messages') without side effects.
Attacks that exploit this kind of access
List unread messages outside the inbox that may need attention. It is categorised as a Read tool in the Personal Mail MCP Server, which means it retrieves data without modifying state.
Register the Personal Mail MCP server in PolicyLayer and add a rule for missed_mail: 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 Personal Mail. Nothing to install.
missed_mail 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 missed_mail 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 missed_mail. 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.
missed_mail is provided by the Personal Mail MCP server (srogerf/personal-mail-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 →