execute_card · Metabase MCP: Risk & Policy

WHAT IT DOES

What execute_card does on Metabase

AI agents invoke execute_card to trigger actions in Metabase. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why execute_card needs a policy

Although the immediate action (retrieving results) might appear read-like, the 'execute' terminology and the fact that saved cards can contain any Metabase operation (queries with side effects, potentially including write or destructive operations depending on permissions) places this in the Execute category.

From the tool's definition Tool name 'execute_card' and description 'Execute a saved Metabase question/card and retrieve results' directly indicate execution of a pre-defined query or operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_card Rate-limited

execute_card stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_card": {
      "limits": [
        {
          "counter": "execute_card_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 execute_card

What does the execute_card tool do? +

Execute a saved Metabase question/card and retrieve results. It is categorised as a Execute tool in the Metabase MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_card? +

Register the Metabase MCP server in PolicyLayer and add a rule for execute_card: 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 execute_card? +

execute_card is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_card? +

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

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

execute_card 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.