create_credential · Databricks Permissions MCP Server MCP

WHAT IT DOES

What create_credential does on Databricks Permissions MCP Server

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

WHY IT NEEDS A POLICY

Why create_credential needs a policy

This tool creates new credentials in a Databricks Unity Catalog. While reversible via deletion, credentials are sensitive security objects—storing them incorrectly or with misconfigurations could expose authentication material. The blast radius includes potential unauthorized access to protected resources.

From the tool's definition Tool name: 'create_credential'. Description states: 'Create a credential in Unity Catalog'. The verb 'create' and the action of adding a new credential object indicates data creation and modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_credential Rate-limited

create_credential 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_credential": {
      "limits": [
        {
          "counter": "create_credential_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 Permissions MCP Server, so you can run agents against it safely.

FAQ

Questions about create_credential

What does the create_credential tool do? +

Create a credential in Unity Catalog with parameters: name (required), credential_type (required), credential_info (required), comment (optional). It is categorised as a Write tool in the Databricks Permissions 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_credential? +

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

What risk level is create_credential? +

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

Can I rate-limit create_credential? +

Yes. Add a rate_limit block to the create_credential 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_credential completely? +

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

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