Deploy (sideload) the Roku app to the device. Roku API: POST http://{host}/plugin_install (Basic Auth: rokudev:{password}) Uses roku-deploy npm to zip and upload the channel. Requires: Developer Mode enabled, device on same network. Ref: developer.roku.com/docs/developer-program/getting-started/d...
AI agents invoke roku_deploy 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.
Roku app deployment executes code on a physical device. While technically reversible through uninstallation, the act of deploying arbitrary application code to a device is a code execution operation with external effects dependent on what app is deployed. An AI agent with this capability could install malicious apps, access device resources, or compromise user privacy.
From the tool's definition Tool performs deployment/sideloading action to device via POST request to /plugin_install endpoint. Description states it 'zip[s] and upload[s] the channel' to the Roku device, which is an active operation that triggers device-side effects (app installation).
Attacks that exploit this kind of access
Deploy (sideload) the Roku app to the device. Roku API: POST http://{host}/plugin_install (Basic Auth: rokudev:{password}) Uses roku-deploy npm to zip and upload the channel. Requires: Developer Mode enabled, device on same network. Ref: developer.roku.com/docs/developer-program/getting-started/developer-setup.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.
Register the Roku MCP Server MCP server in PolicyLayer and add a rule for roku_deploy: 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_deploy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the roku_deploy 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_deploy. 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_deploy 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 →