AI agents call read_dbfs_file to retrieve information from Databricks MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from Databricks File System (DBFS) without modifying, deleting, or executing anything. It has no side effects beyond accessing existing file content. While sensitive data might be exposed depending on DBFS permissions and content, the tool itself is fundamentally a read operation with low severity risk in isolation.
From the tool's definition Tool name is 'read_dbfs_file' and description states 'Read file content from DBFS.' The verb 'read' and lack of any write, delete, or execution keywords confirm this is a retrieval operation.
Documented attack patterns abuse exactly the kind of access read_dbfs_file 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 read_dbfs_file:
{
"version": "1",
"default": "deny",
"tools": {
"read_dbfs_file": {}
}
}read_dbfs_file is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read file content from DBFS. It is categorised as a Read tool in the Databricks MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for read_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.
read_dbfs_file is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_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.
Set action: deny in the PolicyLayer policy for read_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.
read_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.
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.