roku_input · Roku MCP Server MCP: Risk & Policy

WHAT IT DOES

What roku_input does on Roku MCP Server

AI agents invoke roku_input to trigger actions in Roku MCP Server. 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.

WHY IT NEEDS A POLICY

Why roku_input needs a policy

This tool triggers an external operation on a running Roku application by POSTing parameters that affect its runtime behavior. It doesn't just read data or create/modify stored data — it actively sends input events to a live app, making it an Execute-category action. Misuse could cause unintended app behavior or navigation, but blast radius is limited to the targeted device/app session.

From the tool's definition Send custom input/deep-link parameters to the running app... Sends name-value pairs via roInput to the active channel

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

roku_input Rate-limited

roku_input stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "roku_input": {
      "limits": [
        {
          "counter": "roku_input_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Roku MCP Server, so you can run agents against it safely.

FAQ

Questions about roku_input

What does the roku_input tool do? +

Send custom input/deep-link parameters to the running app. Roku API: POST http://{host}:8060/input?{params} Sends name-value pairs via roInput to the active channel. Use for testing deep linking into a running app. Ref: developer.roku.com/docs/developer-program/debugging/external-control-api.md. It is categorised as a Execute tool in the Roku MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on roku_input? +

Register the Roku MCP Server MCP server in PolicyLayer and add a rule for roku_input: 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.

What risk level is roku_input? +

roku_input is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit roku_input? +

Yes. Add a rate_limit block to the roku_input 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.

How do I block roku_input completely? +

Set action: deny in the PolicyLayer policy for roku_input. 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.

What MCP server provides roku_input? +

roku_input 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.