create_catalog · Databricks MCP Server MCP: Risk & Policy

WHAT IT DOES

What create_catalog does on Databricks MCP Server

AI agents use create_catalog 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.

WHY IT NEEDS A POLICY

Why create_catalog needs a policy

This tool creates a new resource (catalog) in Databricks, which is a reversible write operation. It does not execute arbitrary code, delete data, or involve financial transactions. The severity is medium because creating a catalog in a shared data platform could affect access controls and data organization for other users, but the action itself is not destructive and can be undone by deleting the catalog.

From the tool's definition Tool name is 'create_catalog' with description 'Create a catalog with parameters: name, comment'. The action creates a new Unity Catalog entity in Databricks.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_catalog Rate-limited

create_catalog 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_catalog": {
      "limits": [
        {
          "counter": "create_catalog_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Databricks MCP Server, so you can run agents against it safely.

FAQ

Questions about create_catalog

What does the create_catalog tool do? +

Create a catalog with parameters: name, comment. 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 create_catalog? +

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

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

Can I rate-limit create_catalog? +

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

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

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