AI agents use request_download to create or update resources in MCParr Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCParr Server environment.
This tool creates a new download request in the media management system. It is a Write action (adds a new record/request) rather than Destructive, but carries high severity because it can trigger automated downloading of content, consuming storage, bandwidth, and potentially raising copyright/legal concerns if misused by an AI agent at scale.
From the tool's definition "Request a download for a movie or TV show" — initiates a download request in Radarr/Sonarr
Documented attack patterns abuse exactly the kind of access request_download gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCParr Server, and nothing reaches the server without passing your rules. This is the rule we recommend for request_download:
{
"version": "1",
"default": "deny",
"tools": {
"request_download": {
"limits": [
{
"counter": "request_download_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}request_download stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Request a download for a movie or TV show. It is categorised as a Write tool in the MCParr Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCParr Server MCP server in PolicyLayer and add a rule for request_download: 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 MCParr Server. Nothing to install.
request_download is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the request_download 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 request_download. 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.
request_download is provided by the MCParr Server MCP server (jasontulp/mcparr-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCParr Server, 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.
4 MCParr Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.