AI agents use metube_add_download to create or update resources in Metube — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metube environment.
This tool creates new download queue entries (Write category). Severity is medium because: (1) it queues external content downloads which could consume bandwidth/storage, (2) a malicious agent could queue numerous large downloads, but (3) the action is reversible via metube_cancel_add or metube_delete_downloads. It does not execute arbitrary code, delete data, or move money.
From the tool's definition Tool name 'metube_add_download' and server description stating it 'supports operations like queuing URLs' indicates this tool adds/queues new download tasks.
Attacks that exploit this kind of access
metube_add_download. It is categorised as a Write tool in the Metube MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metube MCP server in PolicyLayer and add a rule for metube_add_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 Metube. Nothing to install.
metube_add_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 metube_add_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 metube_add_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.
metube_add_download is provided by the Metube MCP server (junglem0nkey/metube-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →