input_key

Press hardware key (BACK, HOME, ENTER, etc.)

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/input-key.md

WHAT IT DOES

What input_key does on Claude Mobile

AI agents invoke input_key to trigger actions in Claude Mobile. 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.

RISK

Why input_key is rated High

This tool triggers hardware key press actions on a mobile device, which are external operations that cause navigation and UI state changes (e.g., navigating back, returning to home screen, confirming input). These are real-time interactions with a device whose effects depend on the argument provided. While not directly destructive or financial, misuse could disrupt app state or trigger unintended confirmations.

From the tool's definition Press hardware key (BACK, HOME, ENTER, etc.)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs input_key safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For input_key, this is the rule to start with:

input_key Rate-limited

input_key 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": {
    "input_key": {
      "limits": [
        {
          "counter": "input_key_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every input_key call is checked against it from then on.

FAQ

Questions about input_key

What does the input_key tool do? +

Press hardware key (BACK, HOME, ENTER, etc.). It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on input_key? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for input_key: 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 Claude Mobile. Nothing to install.

What risk level is input_key? +

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

Can I rate-limit input_key? +

Yes. Add a rate_limit block to the input_key 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 input_key completely? +

Set action: deny in the PolicyLayer policy for input_key. 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 input_key? +

input_key is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools → High-risk tools on this server →

Across the catalogue

qt_key_press on Qt →send_key_to_window on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →