🗑️ 将文件/目录移到回收站 ~/.trash/（可通过 file_move 还原）。
AI agents call file_trash 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 moves files/directories to a trash folder. While technically reversible via file_move (unlike a permanent delete), it still removes files from their original location and places them in a trash directory. The server has broad Android device control capabilities, and misuse could cause significant data loss if trash is later purged.
From the tool's definition 🗑️ 将文件/目录移到回收站 ~/.trash/（可通过 file_move 还原）
Attacks that exploit this kind of access
🗑️ 将文件/目录移到回收站 ~/.trash/（可通过 file_move 还原）。. 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_trash: 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_trash 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_trash 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_trash. 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_trash 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 →