batch_execute

What batch_execute does on Metabase MCP

AI agents invoke batch_execute to trigger actions in Metabase MCP. 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 batch_execute is rated High

The tool name 'batch_execute' combined with the server's purpose (query and manage Metabase) and the presence of similar execution tools (execute_card, execute_query) indicates this performs execution of database queries or operations. Execution is inherently higher risk than Read/Write due to unpredictable side effects, though without a destructive verb it does not reach Destructive.

From the tool's definition Tool name 'batch_execute' indicates execution of multiple operations; sibling tools show this server executes queries and manages Metabase objects; empty description lowers confidence but context suggests code/query execution.

Risk signalsBulk/mass operation — affects multiple targets

The rule that runs batch_execute safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Metabase MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For batch_execute, this is the rule to start with:

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

Questions about batch_execute