Interact with Apple Messages app - send, read, schedule messages and check unread messages
AI agents use messages 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.
This tool permits creation and modification of messages, which are communications that can reach real people. An AI agent with unsupervised access could send messages to arbitrary contacts, potentially impersonating the user, conducting social engineering, or causing reputational harm. The ability to schedule messages compounds this risk.
From the tool's definition The tool description explicitly states it can 'send, read, schedule messages and check unread messages'. The 'send' and 'schedule messages' capabilities represent Write actions that create new data (messages) in the Messages app.
Documented attack patterns abuse exactly the kind of access messages 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 messages:
{
"version": "1",
"default": "deny",
"tools": {
"messages": {
"limits": [
{
"counter": "messages_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}messages 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 Messages app - send, read, schedule messages and check unread messages. 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 messages: 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.
messages 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 messages 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 messages. 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.
messages 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.