Simulates a key press event with the specified keycode on the connected Android device. Requires the keycode parameter, which is the keycode of the key to press.
AI agents invoke input_press to trigger actions in Ultimate Android MCP. 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 triggers external operations on a physical/virtual Android device by simulating key press events via ADB. It doesn't merely read data, nor does it directly delete or move money, but it executes input actions on the device whose effects depend on the keycode argument (e.g., HOME, BACK, POWER, or arbitrary app interactions).
From the tool's definition Simulates a key press event with the specified keycode on the connected Android device
Documented attack patterns abuse exactly the kind of access input_press gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ultimate Android MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for input_press:
{
"version": "1",
"default": "deny",
"tools": {
"input_press": {
"limits": [
{
"counter": "input_press_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}input_press 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.
Simulates a key press event with the specified keycode on the connected Android device. Requires the keycode parameter, which is the keycode of the key to press. It is categorised as a Execute tool in the Ultimate Android MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ultimate Android MCP server in PolicyLayer and add a rule for input_press: 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 Ultimate Android MCP. Nothing to install.
input_press 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 input_press 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 input_press. 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.
input_press is provided by the Ultimate Android MCP server (oddlyspaced/ultimate-android-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ultimate Android MCP, 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.
35 Ultimate Android MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.