Track app/media lifecycle events. Roku API: GET http://{host}:8060/query/app-state/{appId} Returns: current app state and media lifecycle information. Requires: Developer Mode. Ref: developer.roku.com/docs/developer-program/debugging/external-control-api.md
AI agents call roku_app_state 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 tool retrieves current application and media state information without modifying, executing code, deleting data, or creating financial obligations. It is purely a read operation for inspection and monitoring purposes. Severity is low because querying app state poses minimal risk even if misused by an AI agent—it only exposes monitoring data accessible to developer mode.
From the tool's definition Tool queries app state and media lifecycle information via GET request to /query/app-state/{appId}. The description uses 'Track' and 'query', and the HTTP method is GET, indicating data retrieval only.
Attacks that exploit this kind of access
Track app/media lifecycle events. Roku API: GET http://{host}:8060/query/app-state/{appId} Returns: current app state and media lifecycle information. Requires: Developer Mode. 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_app_state: 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_app_state 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_app_state 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_app_state. 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_app_state 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 →