List inbox messages for a configured Microsoft or Gmail account.
AI agents call mail_inbox 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 email messages from an inbox without creating, modifying, or deleting any data. It has no side effects beyond providing information access. While it accesses personal mail (which may contain sensitive information), the tool itself performs only read operations.
From the tool's definition Tool description explicitly states 'List inbox messages' which is a retrieval operation with no modification capability.
Attacks that exploit this kind of access
List inbox messages for a configured Microsoft or Gmail account. 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 mail_inbox: 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.
mail_inbox 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_inbox 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_inbox. 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_inbox 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 →