Get recently active torrents and IDs of recently removed ones.
AI agents call get_recently_active to retrieve information from Transmission without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about torrent status and history. It retrieves data about active torrents and removed torrent IDs without creating, modifying, deleting, or executing any operations. This is a pure read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_recently_active' and description 'Get recently active torrents and IDs of recently removed ones' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get recently active torrents and IDs of recently removed ones. It is categorised as a Read tool in the Transmission MCP Server, which means it retrieves data without modifying state.
Register the Transmission MCP server in PolicyLayer and add a rule for get_recently_active: 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.
get_recently_active 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_recently_active 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_recently_active. 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_recently_active 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 →