Uninstall an app from the device
AI agents call adb_uninstall_app to permanently remove resources in ADB MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Uninstalling an app is an irreversible operation that removes application code, data, and system state from a device. While not as catastrophic as wiping entire system storage, it cannot be undone without reinstallation and represents permanent loss of application state. This fits the Destructive category rather than Write (reversible modification) or Execute (code execution with argument-dependent effects).
From the tool's definition Tool name 'adb_uninstall_app' with description 'Uninstall an app from the device' indicates irreversible removal of application data and installation.
Attacks that exploit this kind of access
Uninstall an app from the device. It is categorised as a Destructive tool in the ADB MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for adb_uninstall_app: 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 ADB MCP Server. Nothing to install.
adb_uninstall_app 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 adb_uninstall_app 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 adb_uninstall_app. 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.
adb_uninstall_app is provided by the ADB MCP Server MCP server (richard0913/adb-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 →