AI agents invoke input-text to trigger actions in ADB 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.
This tool sends input events to an Android device, which constitutes executing an external operation with real side effects (e.g., filling forms, triggering UI actions, sending messages). It goes beyond a simple read/write of data and interacts with the device's input system. Misuse could lead to unintended actions on the device such as submitting forms, entering credentials, or triggering app behaviors.
From the tool's definition "Input text to the connected Android device" — triggers an external operation (text input) on a physical/virtual Android device via ADB
Documented attack patterns abuse exactly the kind of access input-text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ADB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for input-text:
{
"version": "1",
"default": "deny",
"tools": {
"input-text": {
"limits": [
{
"counter": "input-text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Input text to the connected Android device. It is categorised as a Execute tool in the ADB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for 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 ADB MCP Server. Nothing to install.
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 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 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.
input-text is provided by the ADB MCP Server MCP server (jiantao88/android-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ADB MCP Server, 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.
30 ADB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.