🗑️ 安全删除文件或目录（不可恢复！）。
AI agents call file_delete to permanently remove resources in Android MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently and irreversibly deletes files or directories on an Android device. The description explicitly emphasizes the unrecoverable nature of the deletion ('不可恢复！'). Once invoked by an AI agent, the deleted data cannot be restored, making this a destructive operation. The high severity reflects the potential for significant data loss if misused.
From the tool's definition Tool name: file_delete; Description explicitly states '安全删除文件或目录（不可恢复！）' which translates to 'Securely delete file or directory (cannot be recovered!)', indicating irreversible deletion of data.
Attacks that exploit this kind of access
🗑️ 安全删除文件或目录（不可恢复！）。. It is categorised as a Destructive tool in the Android MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Android MCP Server MCP server in PolicyLayer and add a rule for file_delete: 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 Server. Nothing to install.
file_delete 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 file_delete 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 file_delete. 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.
file_delete is provided by the Android MCP Server MCP server (wujie272/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 →