PullGesture
PullGesture action, Trigger pull down to refresh or pull up actions. Parameters: direction (enum('up', 'down')) - The direction to pull; distance? (number) - The distance to pull (in pixels); duration? (number) - The duration of the pull (in milliseconds); locate? (object) - The element to start ...
This record as markdown: /tools/android/pullgesture.md
What PullGesture does on Android
AI agents invoke PullGesture to trigger actions in Android. 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 |
|---|---|---|---|
locate | object | — | The element to start the pull from (optional) |
distance | number | — | The distance to pull (in pixels) |
duration | number | — | The duration of the pull (in milliseconds) |
direction | string | Yes | The direction to pull |
android.deviceId | string | — | Android device ID (from adb devices) |
android.useScrcpy | boolean | — | Enable scrcpy accelerated screenshots |
android.aiActContext | string | — | Background knowledge passed to aiAct. Default: no extra context. |
android.waitAfterAction | number | — | Wait time in milliseconds after each action execution. Default: 300ms. |
android.replanningCycleLimit | integer | — | Maximum number of replanning cycles for aiAct. Default: model adapter default. |
android.screenshotShrinkFactor | number | — | Screenshot shrink factor before sending images to AI. Default: 1; high values may reduce recognition quality, especially on mobile. |
Parameters from the server's own tool schema.
Why PullGesture is rated High
This tool performs automation actions that execute gestures on a connected Android device, triggering external operations (pull-to-refresh, pull-up actions) whose effects depend on the target application and current state. While not destructive by itself, it has significant side effects as a gesture trigger and belongs in Execute category.
From the tool's definition PullGesture action that 'Trigger pull down to refresh or pull up actions' with parameters for direction, distance, duration, and element location. This executes gestures on the Android device that trigger application-specific behaviors.
Risk signalsHigh parameter count (15 properties)
Attacks that exploit this kind of access
The rule that runs PullGesture safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Android, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For PullGesture, this is the rule to start with:
PullGesture 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 Android, apply this rule, and every PullGesture call is checked against it from then on.
Questions about PullGesture
PullGesture action, Trigger pull down to refresh or pull up actions. Parameters: direction (enum('up', 'down')) - The direction to pull; distance? (number) - The distance to pull (in pixels); duration? (number) - The duration of the pull (in milliseconds); locate? (object) - The element to start the pull from (optional). It is categorised as a Execute tool in the Android MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
PullGesture accepts 10 parameters: locate, distance, duration, direction, android.deviceId, android.useScrcpy, android.aiActContext, android.waitAfterAction, android.replanningCycleLimit, android.screenshotShrinkFactor. Required: direction. The full parameter table on this page comes from the server's own tool schema.
Register the Android MCP server in PolicyLayer and add a rule for PullGesture: 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. Nothing to install.
PullGesture 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 PullGesture 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 PullGesture. 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.
PullGesture is provided by the Android MCP server (@midscene/android-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Android, and thousands of servers like it.
Across the catalogue