AI agents invoke select_file to trigger actions in Apple Notifier. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Opening a native file picker dialog triggers an external OS-level UI operation, which goes beyond passive data retrieval. The dialog could expose the filesystem to the agent and result in file selection that drives subsequent actions. Classified as Execute because it triggers an external OS operation, though no data is read or written by this action alone.
From the tool's definition Open native file picker dialog
Documented attack patterns abuse exactly the kind of access select_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Notifier, and nothing reaches the server without passing your rules. This is the rule we recommend for select_file:
{
"version": "1",
"default": "deny",
"tools": {
"select_file": {
"limits": [
{
"counter": "select_file_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}select_file stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open native file picker dialog. It is categorised as a Execute tool in the Apple Notifier MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Apple Notifier MCP server in PolicyLayer and add a rule for select_file: 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 Notifier. Nothing to install.
select_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the select_file 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 select_file. 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.
select_file is provided by the Apple Notifier MCP server (turlockmike/apple-notifier-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Notifier, 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.
5 Apple Notifier tools catalogued and risk-classified — across an index of 43,000+ MCP servers.