Skip to previous track or restart current track if played more than a few seconds.
AI agents invoke sonos_previous to trigger actions in Sonos Ts. 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 executes a command on an external device (Sonos speaker) that changes its operational state. While not destructive or financial, it is an imperative action with side effects: the playback state will be modified. The user's music listening experience is directly affected.
From the tool's definition Tool description states it 'Skip to previous track or restart current track' — these are direct control actions that trigger state changes in the Sonos device's playback state, analogous to pressing a button on a remote control.
Documented attack patterns abuse exactly the kind of access sonos_previous gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sonos Ts, and nothing reaches the server without passing your rules. This is the rule we recommend for sonos_previous:
{
"version": "1",
"default": "deny",
"tools": {
"sonos_previous": {
"limits": [
{
"counter": "sonos_previous_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}sonos_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.
Skip to previous track or restart current track if played more than a few seconds. It is categorised as a Execute tool in the Sonos Ts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sonos Ts MCP server in PolicyLayer and add a rule for sonos_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 Sonos Ts. Nothing to install.
sonos_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 sonos_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 sonos_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.
sonos_previous is provided by the Sonos Ts MCP server (tommertom/sonos-ts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sonos Ts, 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.
60 Sonos Ts tools catalogued and risk-classified — across an index of 43,000+ MCP servers.