AI agents use move_files to create or update resources in Baidu Pan — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Baidu Pan environment.
Moving files modifies their location within the filesystem but does not execute code, delete data irreversibly, or move money. It is reversible (files can be moved back). While it does alter data organization, it falls under Write category as a metadata modification operation.
From the tool's definition Tool name 'move_files' and description indicating file movement operation ('移动百度网盘中的文件到新目录' translates to 'move files in Baidu Netdisk to new directory'). This is a reversible modification of file metadata/location rather than deletion or execution.
Attacks that exploit this kind of access
移动百度网盘中的文件到新目录. It is categorised as a Write tool in the Baidu Pan MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Baidu Pan MCP server in PolicyLayer and add a rule for move_files: 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 Baidu Pan. Nothing to install.
move_files is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the move_files 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 move_files. 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.
move_files is provided by the Baidu Pan MCP server (xileforcly/baidu-pan-mcp-server). 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 →