AI agents invoke stop_playback to trigger actions in LLM Jukebox. 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 that controls an external audio playback system. While the operation itself is not destructive, reversible, or data-modifying, it performs an action on a running process. It falls under Execute rather than Write because it does not create, modify, or store data—it merely halts an ongoing operation.
From the tool's definition Tool name 'stop_playback' and description 'Stop any currently playing song' indicate it triggers an external operation (playback control) whose effect depends on the current state of the audio system.
Documented attack patterns abuse exactly the kind of access stop_playback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LLM Jukebox, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_playback:
{
"version": "1",
"default": "deny",
"tools": {
"stop_playback": {
"limits": [
{
"counter": "stop_playback_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_playback 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.
Stop any currently playing song. It is categorised as a Execute tool in the LLM Jukebox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LLM Jukebox MCP server in PolicyLayer and add a rule for stop_playback: 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 LLM Jukebox. Nothing to install.
stop_playback 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 stop_playback 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 stop_playback. 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.
stop_playback is provided by the LLM Jukebox MCP server (jabberjabberjabber/llm-jukebox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LLM Jukebox, 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.
3 LLM Jukebox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.