AI agents use queue_track to create or update resources in Roon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Roon environment.
queue_track modifies the music queue by adding tracks, which is a reversible write operation. While it changes system state, the change is non-destructive (can be undone by removing items), requires no code execution, and has minimal blast radius if misused by an AI agent. This is classified as Write with low severity.
From the tool's definition Tool description states 'Add a track or album to the end of the queue' — this modifies the queue state by appending items, which is a reversible write operation. The tool does not delete, execute arbitrary code, or cause financial transactions.
Attacks that exploit this kind of access
Add a track or album to the end of the queue without interrupting what. It is categorised as a Write tool in the Roon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Roon MCP server in PolicyLayer and add a rule for queue_track: 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 Roon. Nothing to install.
queue_track 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 queue_track 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 queue_track. 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.
queue_track is provided by the Roon MCP server (txagscott/roon-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 →