AI agents call mail_get_total_inbox_count 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 aggregate metadata (inbox message count) from the Mail application. It performs a read-only query with no capability to modify, delete, or execute actions. The blast radius of misuse is minimal—an agent could only obtain a count of messages, which is low-sensitivity information. No side effects, no data modification, and no external operations triggered.
From the tool's definition Tool name 'mail_get_total_inbox_count' and description 'Get total message count in inbox' indicate a retrieval operation that queries data without modification or side effects.
Attacks that exploit this kind of access
Get total message count in inbox. 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_total_inbox_count: 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_total_inbox_count 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_total_inbox_count 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_total_inbox_count. 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_total_inbox_count 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 →