AI agents invoke search_and_play to trigger actions in Roon. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool combines a search with an immediate playback action on an external audio device. It goes beyond a read operation because it actively changes the device state (starts playing music), making it an Execute category. Misuse could result in unexpected audio playback, but the blast radius is limited to audio disruption with no data loss or financial impact.
From the tool's definition 'Search the Roon library and immediately play the best match' — triggers external playback operation on a physical device
Attacks that exploit this kind of access
Search the Roon library and immediately play the best match on the FiiO M21. It is categorised as a Execute tool in the Roon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Roon MCP server in PolicyLayer and add a rule for search_and_play: 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.
search_and_play is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the search_and_play 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 search_and_play. 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.
search_and_play 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 →