Send text input to Android TV. Requires pairing first (use atv_start_pairing).
AI agents invoke atv_input_text to trigger actions in AndroidTVMCP. 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.
This tool sends text input to an Android TV device, triggering an external operation on the device. While not destructive or financial, it executes an action on a remote device that could be used to interact with apps, enter credentials, or trigger commands — making it Execute rather than Write, since it controls a physical device's input.
From the tool's definition Send text input to Android TV
Documented attack patterns abuse exactly the kind of access atv_input_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AndroidTVMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for atv_input_text:
{
"version": "1",
"default": "deny",
"tools": {
"atv_input_text": {
"limits": [
{
"counter": "atv_input_text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}atv_input_text 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.
Free to start. No card required.
Send text input to Android TV. Requires pairing first (use atv_start_pairing). It is categorised as a Execute tool in the AndroidTVMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AndroidTV MCP server in PolicyLayer and add a rule for atv_input_text: 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 AndroidTVMCP. Nothing to install.
atv_input_text 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 atv_input_text 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 atv_input_text. 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.
atv_input_text is provided by the AndroidTV MCP server (pigeek/androidtvmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AndroidTVMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 AndroidTVMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.