Dump current screen of Android device.
AI agents call dump_screen to retrieve information from Android Device without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool captures the current screen contents for viewing/analysis purposes only. This is a read-only operation with no side effects, no data modification, and no capability to execute commands or delete data. The blast radius is minimal—it exposes only what is currently visible on the device screen. It belongs in the Read category.
From the tool's definition dump_screen: Dump current screen of Android device. This retrieves the current visual state of the device without modifying, deleting, or executing arbitrary operations.
Attacks that exploit this kind of access
Dump current screen of Android device. It is categorised as a Read tool in the Android Device MCP Server, which means it retrieves data without modifying state.
Register the Android Device MCP server in PolicyLayer and add a rule for dump_screen: 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 Device. Nothing to install.
dump_screen 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 dump_screen 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 dump_screen. 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.
dump_screen is provided by the Android Device MCP server (prashant1507/android-device-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →