Delete an existing AVD.
AI agents call delete_avd to permanently remove resources in Android Emulator — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes an AVD and its associated data without possibility of recovery (unless backups exist outside the tool's scope). Deletion is the hallmark of the Destructive category. While the blast radius is somewhat limited to the local development environment (not production systems), the irreversibility and potential loss of development work justifies 'high' severity.
From the tool's definition Tool name 'delete_avd' combined with description 'Delete an existing AVD' explicitly performs irreversible deletion of Android Virtual Device configurations.
Attacks that exploit this kind of access
Delete an existing AVD. It is categorised as a Destructive tool in the Android Emulator MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Android Emulator MCP server in PolicyLayer and add a rule for delete_avd: 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 Emulator. Nothing to install.
delete_avd 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 delete_avd 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 delete_avd. 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.
delete_avd is provided by the Android Emulator MCP server (janjetze/android-emulator-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 →