Copy file from source to destination.
AI agents use copy_file to create or update resources in Claude File Management Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude File Management Server environment.
Copying a file is a reversible write operation: it creates/modifies data on the filesystem (the destination) without destroying the original or being irreversible. The blast radius is minimal — accidental copies waste storage but can be deleted. No code execution, financial impact, or permanent destruction occurs.
From the tool's definition Tool name 'copy_file' with description 'Copy file from source to destination.' — this creates a duplicate of a file, modifying the destination filesystem by adding new data.
Attacks that exploit this kind of access
Copy file from source to destination. It is categorised as a Write tool in the Claude File Management Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude File Management Server MCP server in PolicyLayer and add a rule for copy_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 Claude File Management Server. Nothing to install.
copy_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 copy_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 copy_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.
copy_file is provided by the Claude File Management Server MCP server (vipin1000/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 →