droid_input
Relay one explicit input event to a user-owned Android device: target (preferred; resolves visible text/content-description/resource-id), tap (x,y), text, key, or swipe. Inspect with droid_ui_elements first. Stop on CAPTCHA, verification, rate-limit, or service block screens; never use this tool ...
This record as markdown: /tools/io-github-kivanccakmak-yaver/droid-input.md
What droid_input does on Yaver
AI agents invoke droid_input to trigger actions in Yaver. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
x | integer | — | tap X |
y | integer | — | tap Y |
x1 | integer | — | swipe start X |
x2 | integer | — | swipe end X |
y1 | integer | — | swipe start Y |
y2 | integer | — | swipe end Y |
dur | integer | — | swipe duration ms (default 300) |
text | string | — | text to type (spaces handled) |
type | string | Yes | |
device | string | — | adb serial (default: first attached device) |
target | string | — | Visible text, content description, or resource id. Ambiguous matches fail without tapping. |
keycode | integer | — | Android keyevent code |
Parameters from the server's own tool schema.
Why droid_input is rated High
Executes arbitrary UI interactions on a real Android device, enabling broad automated control.
From the tool's definition Relay one explicit input event to a user-owned Android device
Risk signalsHigh parameter count (13 properties)
Attacks that exploit this kind of access
The rule that runs droid_input safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For droid_input, this is the rule to start with:
droid_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every droid_input call is checked against it from then on.
Questions about droid_input
Relay one explicit input event to a user-owned Android device: target (preferred; resolves visible text/content-description/resource-id), tap (x,y), text, key, or swipe. Inspect with droid_ui_elements first. Stop on CAPTCHA, verification, rate-limit, or service block screens; never use this tool to evade them. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
droid_input accepts 12 parameters: x, y, x1, x2, y1, y2, dur, text, type, device, target, keycode. Required: type. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for droid_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 Yaver. Nothing to install.
droid_input 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 droid_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.
Set action: deny in the PolicyLayer policy for droid_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.
droid_input is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
Across the catalogue