AI agents call mail_get_accounts to retrieve information from Mcp Mac without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account metadata (names only) from the Mail application without side effects. It is a read-only query operation. Severity is low because account names alone pose minimal risk; they do not grant access to email content, enable financial transactions, or permit destructive actions. The blast radius of misuse is limited to information disclosure of account names.
From the tool's definition Tool name is 'mail_get_accounts' and description states 'Get list of all Mail account names' — a pure retrieval operation with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get list of all Mail account names. It is categorised as a Read tool in the Mcp Mac MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mac MCP server in PolicyLayer and add a rule for mail_get_accounts: 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 Mac. Nothing to install.
mail_get_accounts 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_get_accounts 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_get_accounts. 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_get_accounts is provided by the Mcp Mac MCP server (samicokar/mcp-mac). 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 →