AI agents invoke input_text to trigger actions in Adb. 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 executes an ADB input command to type text into the currently focused field on a remote Android device. It triggers an external operation (device input) whose effects depend on arguments — text could be injected into any active field including sensitive inputs. Categorized as Execute rather than Write because it runs an ADB command on a remote device rather than modifying structured data reversibly.
From the tool's definition 'input_text' - inputs text into Android device; 'Enables remote control of Android devices via ADB, including screen operations, input'
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, 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.
输入文本. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adb 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. 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 (wolfcoming/adb_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Adb, 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.
48 Adb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.