Get a direct .torrent file download URL from an info_hash. Use when the user specifically wants a .torrent file rather than a magnet link (magnet links are already in search_content results). Returns a single URL the user can open in their browser or torrent client.
AI agents call get_torrent_url to retrieve information from TorrentClaw-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite facilitating access to torrent files (which may be used for copyright infringement), the tool itself is a passive read operation that retrieves and returns a URL. It does not execute code, modify data, delete content, or commit financial transactions. The actual download and use of the torrent file occurs outside the tool's scope.
From the tool's definition Tool description states it 'Get[s] a direct .torrent file download URL' and 'Returns a single URL the user can open'. This is retrieval of a URL resource with no side effects on the server.
Attacks that exploit this kind of access
Get a direct .torrent file download URL from an info_hash. Use when the user specifically wants a .torrent file rather than a magnet link (magnet links are already in search_content results). Returns a single URL the user can open in their browser or torrent client. It is categorised as a Read tool in the TorrentClaw-MCP MCP Server, which means it retrieves data without modifying state.
Register the TorrentClaw- MCP server in PolicyLayer and add a rule for get_torrent_url: 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 TorrentClaw-MCP. Nothing to install.
get_torrent_url is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_torrent_url 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 get_torrent_url. 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.
get_torrent_url is provided by the TorrentClaw- MCP server (torrentclaw/torrentclaw-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 →