Clear app data for a specific app on the connected Android device
AI agents call clear_app_data to permanently remove resources in Espresso — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes stored data associated with an app on an Android device. App data includes caches, databases, preferences, and files that cannot be recovered once cleared. The operation is destructive and cannot be undone, making it Destructive rather than Write. The high severity reflects the permanent loss of user data and potential impact on app functionality and user state.
From the tool's definition clear_app_data: 'Clear app data for a specific app on the connected Android device' — the operation removes app data, which is irreversible.
Attacks that exploit this kind of access
Clear app data for a specific app on the connected Android device. It is categorised as a Destructive tool in the Espresso MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Espresso MCP server in PolicyLayer and add a rule for clear_app_data: 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 Espresso. Nothing to install.
clear_app_data is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_app_data 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 clear_app_data. 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.
clear_app_data is provided by the Espresso MCP server (vs4vijay/espresso-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 →