databricks_table_preview

A read tool on the Databricks MCP server.

SERVERDatabricks MCP Server SOURCEpypi:databricks-sdk-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-pramodbhatofficial-databricks-sdk-mcp/databricks-table-preview.md

WHAT IT DOES

What databricks_table_preview does on Databricks MCP Server

AI agents call databricks_table_preview to retrieve information from Databricks MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why databricks_table_preview is rated Low

The term 'preview' in the context of database tools typically means displaying a sample or summary of data for inspection purposes. This is a non-destructive, non-modifying operation that queries data. Despite the empty description reducing confidence slightly, the tool name itself clearly indicates a read operation.

From the tool's definition Tool name 'databricks_table_preview' contains 'preview' which strongly suggests retrieving a sample or view of table data without modification.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs databricks_table_preview safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Databricks MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For databricks_table_preview, this is the rule to start with:

databricks_table_preview Allowed

databricks_table_preview is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "databricks_table_preview": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Databricks MCP Server, apply this rule, and every databricks_table_preview call is checked against it from then on.

FAQ

Questions about databricks_table_preview

What does the databricks_table_preview tool do? +

databricks_table_preview is a read tool on the Databricks MCP Server MCP server. It is categorised as a Read tool in the Databricks MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on databricks_table_preview? +

Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for databricks_table_preview: 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 databricks_table_preview? +

databricks_table_preview is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit databricks_table_preview? +

Yes. Add a rate_limit block to the databricks_table_preview 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 databricks_table_preview completely? +

Set action: deny in the PolicyLayer policy for databricks_table_preview. 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 databricks_table_preview? +

databricks_table_preview is provided by the Databricks MCP Server MCP server (pypi:databricks-sdk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Databricks MCP Server, and thousands of servers like it.

This server

All 262 Databricks MCP Server tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →