android_screen
AI agents call android_screen to retrieve information from Android MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screen capture is fundamentally a read operation—it retrieves visual/sensor data from the device without modifying state. However, severity is elevated to 'medium' because screen captures can expose sensitive information (passwords, personal data, financial details, private communications) depending on what is displayed.
From the tool's definition Tool name 'android_screen' combined with server context indicating 'screen capture' capability suggests data retrieval without modification. Empty description reduces specificity.
Attacks that exploit this kind of access
android_screen. It is categorised as a Read tool in the Android MCP MCP Server, which means it retrieves data without modifying state.
Register the Android MCP server in PolicyLayer and add a rule for android_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 MCP. Nothing to install.
android_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 android_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 android_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.
android_screen is provided by the Android MCP server (steph-ux/android-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 →