inject-input

THE RISK

High Risk

Why inject-input needs a policy

This tool executes input events on an Android device, simulating physical user interactions. It triggers external operations (touch/key events via ADB input commands) whose effects depend on arguments - e.g., tapping UI elements, entering text, or pressing keys. These actions can cause arbitrary app-level effects (submitting forms, navigating, triggering purchases) making misuse potentially high-impact.

From the tool's definition Simulate user input interactions (tap, text, swipe, keyevents) or click by UI element

Documented attack patterns abuse exactly the kind of access inject-input gives an agent:

POLICY

How to control inject-input

PolicyLayer is an MCP gateway — it sits between your AI agents and Android Mcp Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for inject-input:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "inject-input": {
      "limits": [
        {
          "counter": "inject-input_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

inject-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.

Create a free account and register Android Mcp Toolkit — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Android Mcp Toolkit tools

Execute manage-logcat Unified tool to read logs, capture crashes, check ANRs, and clear buffers. Write convert-svg-to-android-drawable Convert SVG markup or files into Android VectorDrawable XML quickly, optionally writing to Read dump-ui-hierarchy Capture the current UI hierarchy as XML using uiautomator. Read estimate-text-length-difference Compare original and translated text lengths to detect layout risk; configurable tolerance Read get-current-activity Inspect current focused app/window via dumpsys window. Read take-screenshot Capture device screenshot and save to a local file.

All 7 Android Mcp Toolkit tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Android Mcp Toolkit → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about inject-input

What does the inject-input tool do? +

Simulate user input interactions (tap, text, swipe, keyevents) or click by UI element. It is categorised as a Execute tool in the Android Mcp Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on inject-input? +

Register the Android Mcp Toolkit MCP server in PolicyLayer and add a rule for inject-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 Android Mcp Toolkit. Nothing to install.

What risk level is inject-input? +

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

Can I rate-limit inject-input? +

Yes. Add a rate_limit block to the inject-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 inject-input completely? +

Set action: deny in the PolicyLayer policy for inject-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 inject-input? +

inject-input is provided by the Android Mcp Toolkit MCP server (nam0101/android-mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Android Mcp Toolkit tool call.

Start from Android Mcp Toolkit, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →