Query current video/audio streaming state. Roku API: GET http://{host}:8060/query/media-player Returns: state (play/pause/buffer/stop/close), position (ms), duration (ms), audio format, video format, container, DRM type (widevine/playready/none), bandwidth, buffering progress. Ref: developer.roku...
AI agents call roku_media_player to retrieve information from Roku MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query operation that retrieves real-time media playback information without side effects. The GET-only API design and return of status fields (play/pause/buffer/stop/close state, timestamps, codec information) confirm it performs information retrieval only.
From the tool's definition Tool queries current streaming state via GET request. Description states "Query current video/audio streaming state" and returns only read-only status information: state, position, duration, formats, DRM type, bandwidth, buffering progress.
Attacks that exploit this kind of access
Query current video/audio streaming state. Roku API: GET http://{host}:8060/query/media-player Returns: state (play/pause/buffer/stop/close), position (ms), duration (ms), audio format, video format, container, DRM type (widevine/playready/none), bandwidth, buffering progress. Ref: developer.roku.com/docs/developer-program/debugging/external-control-api.md. It is categorised as a Read tool in the Roku MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Roku MCP Server MCP server in PolicyLayer and add a rule for roku_media_player: 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 Roku MCP Server. Nothing to install.
roku_media_player 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 roku_media_player 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 roku_media_player. 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.
roku_media_player is provided by the Roku MCP Server MCP server (maskelog/roku-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 →