Interact with Apple Mail app - read unread emails, search emails, and send emails
AI agents use mail to create or update resources in Apple MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Apple MCP environment.
The ability to send emails on behalf of the user represents a capability to create and transmit data with external communication effects. While reading and searching are Read operations, the send functionality dominates the risk profile and makes this a Write tool.
From the tool's definition Tool can 'send emails' which creates and transmits new messages, a reversible write operation. Also includes 'read unread emails' and 'search emails' which are read-only, but the send capability makes this a Write tool overall.
Documented attack patterns abuse exactly the kind of access mail gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mail:
{
"version": "1",
"default": "deny",
"tools": {
"mail": {
"limits": [
{
"counter": "mail_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mail stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Interact with Apple Mail app - read unread emails, search emails, and send emails. It is categorised as a Write tool in the Apple MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Apple MCP server in PolicyLayer and add a rule for 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 Apple MCP. Nothing to install.
mail is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the 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 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.
mail is provided by the Apple MCP server (jxnl/apple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Apple MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.