Query the currently running/active app. Roku API: GET http://{host}:8060/query/active-app Returns: id, name, version of the foreground app. Ref: developer.roku.com/docs/developer-program/debugging/external-control-api.md
AI agents call roku_active_app 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 only retrieves information about the currently active application on a Roku device. It performs a read-only query operation using HTTP GET, returns static data about the running app, and produces no side effects. The blast radius if misused is minimal—an agent could only discover which app is running, which is low-risk information. This clearly falls under the Read category.
From the tool's definition Tool name is 'roku_active_app', description states 'Query the currently running/active app', and the API endpoint is a GET request that 'Returns: id, name, version of the foreground app' with no modification or side effects.
Attacks that exploit this kind of access
Query the currently running/active app. Roku API: GET http://{host}:8060/query/active-app Returns: id, name, version of the foreground app. 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_active_app: 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_active_app 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_active_app 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_active_app. 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_active_app 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 →