AI agents invoke download_and_play 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.
The tool likely downloads files from the internet (external operation with side effects) and triggers audio playback on the host system. This constitutes executing external operations (network download + system audio playback). Severity is high because an AI agent could misuse this to download arbitrary content from YouTube and play it, consuming storage and bandwidth. Confidence is reduced due to empty description.
From the tool's definition Tool name 'download_and_play' combined with server description: 'download videos as MP3 files, and play audio with playback controls.' The name implies downloading content from YouTube and triggering audio playback.
Documented attack patterns abuse exactly the kind of access download_and_play 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 download_and_play:
{
"version": "1",
"default": "deny",
"tools": {
"download_and_play": {
"limits": [
{
"counter": "download_and_play_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}download_and_play 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.
download_and_play. 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 download_and_play: 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.
download_and_play 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 download_and_play 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 download_and_play. 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.
download_and_play 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.