AI agents use move_files_by_glob 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.
Moving files is a reversible write operation that modifies data locations without permanent deletion. While the operation affects the filesystem, files can be moved back or recovered. This is categorized as Write rather than Destructive because the data itself is not deleted or overwritten—only its location changes.
From the tool's definition Tool description states: 'Move all files matching a glob pattern from source_dir into destination_dir.' This is a file movement operation that modifies the filesystem by relocating files.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Move all files matching a glob pattern from source_dir into destination_dir. 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_files_by_glob: 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_files_by_glob 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_by_glob 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_by_glob. 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_by_glob 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 →