update_model · Metabase MCP: Risk & Policy

WHAT IT DOES

What update_model does on Metabase

AI agents use update_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 update_model needs a policy

The tool modifies an existing model in Metabase, which is a reversible Write operation. While the description is empty (lowering confidence slightly), the name and server context strongly indicate it updates saved queries or analytics models. This is more severe than Read but less severe than Destructive (models can be reverted/edited further).

From the tool's definition Tool name is 'update_model'; in Metabase context, models are saved queries/data structures. 'Update' indicates modification of existing data/configuration.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_model Rate-limited

update_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": {
    "update_model": {
      "limits": [
        {
          "counter": "update_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 update_model

What does the update_model tool do? +

update_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 update_model? +

Register the Metabase MCP server in PolicyLayer and add a rule for update_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 update_model? +

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

Can I rate-limit update_model? +

Yes. Add a rate_limit block to the update_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 update_model completely? +

Set action: deny in the PolicyLayer policy for update_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 update_model? +

update_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.