Add a torrent from magnet link, HTTP URL, or local file path.
AI agents use add_torrent to create or update resources in Transmission — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Transmission environment.
This is a Write operation because it creates/adds a new torrent to the transmission queue, modifying the client's state reversibly. While the actual download consequences depend on torrent content, the tool itself performs data creation rather than deletion or code execution.
From the tool's definition Tool description states 'Add a torrent' which creates a new torrent entry in the transmission client. The tool accepts magnet links, HTTP URLs, or file paths as input, initiating a download/addition operation.
Attacks that exploit this kind of access
Add a torrent from magnet link, HTTP URL, or local file path. It is categorised as a Write tool in the Transmission MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Transmission MCP server in PolicyLayer and add a rule for add_torrent: 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 Transmission. Nothing to install.
add_torrent 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 add_torrent 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 add_torrent. 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.
add_torrent is provided by the Transmission MCP server (philogicae/transmission-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 →