This record as markdown: /tools/android/take-screenshot.md
What take_screenshot does on Android
AI agents call take_screenshot to retrieve information from Android without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
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 take_screenshot is rated Low
This tool captures visual data from the Android screen without modifying, executing, or deleting anything. It is a passive observation operation with no lasting impact beyond reading the current state.
From the tool's definition Tool name 'take_screenshot' and description 'Capture screenshot of current page/screen' indicate data retrieval with no modifications or side effects.
Attacks that exploit this kind of access
The rule that runs take_screenshot 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 take_screenshot, this is the rule to start with:
take_screenshot is read-only, so it stays allowed. 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 take_screenshot call is checked against it from then on.
Questions about take_screenshot
Capture screenshot of current page/screen. It is categorised as a Read tool in the Android MCP Server, which means it retrieves data without modifying state.
take_screenshot accepts 6 parameters: android.deviceId, android.useScrcpy, android.aiActContext, android.waitAfterAction, android.replanningCycleLimit, android.screenshotShrinkFactor. 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 take_screenshot: 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.
take_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the take_screenshot 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 take_screenshot. 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.
take_screenshot 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.
This server
Across the catalogue