Query app performance metrics (CPU/memory). Roku API: GET http://{host}:8060/query/chanperf Returns: CPU utilization, memory usage, and other perf metrics. Requires: Developer Mode. Ref: developer.roku.com/docs/developer-program/debugging/external-control-api.md
AI agents call roku_perf 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 diagnostic performance data without side effects. It uses a GET request (inherently read-only), returns telemetry information, and does not modify application state, execute code, or trigger external operations. The requirement for Developer Mode is a deployment prerequisite, not an elevation of runtime risk.
From the tool's definition Tool queries performance metrics (CPU/memory) via GET request to /query/chanperf endpoint. Description states 'Query app performance metrics' with no modification, deletion, or execution capabilities. Returns read-only diagnostic data.
Attacks that exploit this kind of access
Query app performance metrics (CPU/memory). Roku API: GET http://{host}:8060/query/chanperf Returns: CPU utilization, memory usage, and other perf metrics. 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_perf: 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_perf 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_perf 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_perf. 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_perf 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 →