Medium Risk

copy_dbfs_file

Copy a file in DBFS from source to destination.

How to control copy_dbfs_file ↓

What copy_dbfs_file does on Databricks MCP Server

AI agents use copy_dbfs_file to create or update resources in Databricks MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Databricks MCP Server environment.

Medium Risk

Why copy_dbfs_file needs a policy

Copying a file is a write operation that creates or modifies data reversibly. The action itself is non-destructive and can be undone (by deleting the copy), so it does not qualify as Destructive. The severity is medium because unintended file copies could consume storage resources or create security/compliance issues if sensitive data is copied to unexpected locations, but the operation remains reversible.

From the tool's definition Tool name is 'copy_dbfs_file' and description states 'Copy a file in DBFS from source to destination.' This creates a duplicate file at the destination location.

Documented attack patterns abuse exactly the kind of access copy_dbfs_file gives an agent:

How to control copy_dbfs_file

PolicyLayer is an MCP gateway — it sits between your AI agents and Databricks MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for copy_dbfs_file:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "copy_dbfs_file": {
      "limits": [
        {
          "counter": "copy_dbfs_file_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

copy_dbfs_file stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Databricks MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about copy_dbfs_file

What does the copy_dbfs_file tool do? +

Copy a file in DBFS from source to destination. It is categorised as a Write tool in the Databricks MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on copy_dbfs_file? +

Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for copy_dbfs_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 Databricks MCP Server. Nothing to install.

What risk level is copy_dbfs_file? +

copy_dbfs_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit copy_dbfs_file? +

Yes. Add a rate_limit block to the copy_dbfs_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.

How do I block copy_dbfs_file completely? +

Set action: deny in the PolicyLayer policy for copy_dbfs_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.

What MCP server provides copy_dbfs_file? +

copy_dbfs_file is provided by the Databricks MCP Server MCP server (pulkitxchadha/awesome-databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Databricks MCP Server tool call.

Start from Databricks MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

86 Databricks MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.