AI agents call dbfs_delete to permanently remove resources in Databricks MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from DBFS without possibility of recovery through normal means. Destructive operations carry higher severity than Execute or Write because the effects cannot be undone. In a data platform context, DBFS deletion could impact multiple downstream jobs, pipelines, and users depending on that data. Confidence is high because the intent is unambiguous from both name and description.
From the tool's definition Tool name 'dbfs_delete' and description 'Delete a DBFS path' indicate irreversible deletion of data stored in Databricks File System (DBFS).
Documented attack patterns abuse exactly the kind of access dbfs_delete gives an agent:
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 dbfs_delete:
{
"version": "1",
"default": "deny",
"hide": [
"dbfs_delete"
]
}dbfs_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a DBFS path. It is categorised as a Destructive tool in the Databricks MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for dbfs_delete: 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.
dbfs_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the dbfs_delete 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 dbfs_delete. 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.
dbfs_delete is provided by the Databricks MCP Server MCP server (markov-kernel/databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
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.
38 Databricks MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.