AI agents invoke itunes_previous to trigger actions in MCP-AppleMusic. 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.
This tool triggers an external operation (controlling Apple Music playback via AppleScript) to navigate to the previous track. It executes an action on an external application rather than simply reading data or writing/modifying stored data. The blast radius is low as it only affects music playback state.
From the tool's definition Return to the previous track
Documented attack patterns abuse exactly the kind of access itunes_previous gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-AppleMusic, and nothing reaches the server without passing your rules. This is the rule we recommend for itunes_previous:
{
"version": "1",
"default": "deny",
"tools": {
"itunes_previous": {
"limits": [
{
"counter": "itunes_previous_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} itunes_previous 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.
Return to the previous track. It is categorised as a Execute tool in the MCP-AppleMusic MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP-AppleMusic MCP server in PolicyLayer and add a rule for itunes_previous: 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-AppleMusic. Nothing to install.
itunes_previous 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 itunes_previous 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 itunes_previous. 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.
itunes_previous is provided by the MCP-AppleMusic MCP server (kennethreitz/mcp-applemusic). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-AppleMusic, 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.
10 MCP-AppleMusic tools catalogued and risk-classified — across an index of 43,000+ MCP servers.