AI agents use move_file to create or update resources in Demo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Demo environment.
File movement is a reversible write operation that modifies the filesystem state. While not destructive (the file is not deleted), it alters data organization and could disrupt application logic or workflows if misapplied. Severity is high because an agent could move critical files to unexpected locations, breaking system functionality, though the operation itself is theoretically reversible by moving the file back.
From the tool's definition Tool description states 'Move a file from source_path to destination_path', which modifies file locations and metadata. 'Move' is a write operation that changes file organization without deletion.
Attacks that exploit this kind of access
Move a file from source_path to destination_path inside MCP_FILE_OPS_ROOT. It is categorised as a Write tool in the Demo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Demo MCP server in PolicyLayer and add a rule for move_file: 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 Demo. Nothing to install.
move_file 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_file 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_file. 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_file is provided by the Demo MCP server (penguinszp001/mcp-server-demo). 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 →