create_model · Metabase MCP: Risk & Policy

WHAT IT DOES

What create_model does on Metabase

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

WHY IT NEEDS A POLICY

Why create_model needs a policy

Based on the tool name 'create_model' and the pattern of sibling creation tools on the Metabase MCP server, this tool most likely creates a new model object (a saved query or data model in Metabase). Model creation is a reversible Write operation—models can be deleted or modified later.

From the tool's definition Tool named 'create_model' with empty description; sibling tools include 'create_card', 'create_dashboard', 'create_collection' which are Write operations in Metabase.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_model Rate-limited

create_model 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_model": {
      "limits": [
        {
          "counter": "create_model_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 Metabase, so you can run agents against it safely.

FAQ

Questions about create_model

What does the create_model tool do? +

create_model. It is categorised as a Write tool in the Metabase 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_model? +

Register the Metabase MCP server in PolicyLayer and add a rule for create_model: 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 Metabase. Nothing to install.

What risk level is create_model? +

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

Can I rate-limit create_model? +

Yes. Add a rate_limit block to the create_model 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_model completely? +

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

create_model is provided by the Metabase MCP server (voducdan/matebase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.