favorite_dashboard · Metabase MCP Server MCP: Risk & Policy

WHAT IT DOES

What favorite_dashboard does on Metabase MCP Server

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

WHY IT NEEDS A POLICY

Why favorite_dashboard needs a policy

This tool modifies user preference data by marking a dashboard as a favorite. It is a reversible write action with minimal blast radius — it only affects the current user's bookmarks and has no impact on data, queries, or shared resources.

From the tool's definition Mark a dashboard as favorite - bookmarks/favorites are a reversible write operation (can be un-favorited)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

favorite_dashboard Rate-limited

favorite_dashboard 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": {
    "favorite_dashboard": {
      "limits": [
        {
          "counter": "favorite_dashboard_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about favorite_dashboard

What does the favorite_dashboard tool do? +

Mark a dashboard as favorite for quick access - use this to bookmark frequently accessed analytical views. It is categorised as a Write tool in the Metabase 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 favorite_dashboard? +

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

What risk level is favorite_dashboard? +

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

Can I rate-limit favorite_dashboard? +

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

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

favorite_dashboard is provided by the Metabase MCP Server MCP server (thangnm93/metabase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.