Download a file from a direct URL (or YouTube/video site via yt-dlp) and optionally organize it into Jellyfin. Use this instead of download_add for direct HTTP links, Google Drive, and YouTube-supported sites. Runs as a background job.
AI agents invoke download_direct to trigger actions in Mediabox MCP. 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 an external download process (via HTTP or yt-dlp) and optionally modifies the media library by organizing files into Jellyfin. It triggers external operations whose effects depend on the URL argument, including running yt-dlp as a subprocess. The blast radius is high because it can fetch arbitrary content from the internet, write files to the server, and modify the media library organization.
From the tool's definition 'Download a file from a direct URL (or YouTube/video site via yt-dlp) and optionally organize it into Jellyfin. Runs as a background job.'
Documented attack patterns abuse exactly the kind of access download_direct gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mediabox MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for download_direct:
{
"version": "1",
"default": "deny",
"tools": {
"download_direct": {
"limits": [
{
"counter": "download_direct_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}download_direct 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 a file from a direct URL (or YouTube/video site via yt-dlp) and optionally organize it into Jellyfin. Use this instead of download_add for direct HTTP links, Google Drive, and YouTube-supported sites. Runs as a background job. It is categorised as a Execute tool in the Mediabox MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mediabox MCP server in PolicyLayer and add a rule for download_direct: 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 Mediabox MCP. Nothing to install.
download_direct 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_direct 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_direct. 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_direct is provided by the Mediabox MCP server (juancmpdev/mediabox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mediabox MCP, 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.
30 Mediabox MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.