# execute_query

Execute a SQL query against a Metabase database

Agent View of the PolicyLayer registry record for `execute_query`. HTML page: https://policylayer.com/tools/zsh52013148087-metabase-mcp/execute-query

## Facts

- Tool: `execute_query`
- Server: Metabase Analytics Integration Server (`zsh52013148087/metabase-mcp`) — https://policylayer.com/tools/zsh52013148087-metabase-mcp.md
- Homepage: https://github.com/zsh52013148087/metabase-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 3
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `query` | string | no | SQL query to execute |
| `database_id` | number | no | ID of the database to query |
| `native_parameters` | array | no | Optional parameters for the query |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "execute_query",
    "arguments": {}
  }
}
```

## Why execute_query is rated High

SQL query execution is fundamentally an Execute-category risk because the effects are entirely argument-dependent: queries could SELECT (Read), INSERT/UPDATE (Write), DROP/DELETE (Destructive), or trigger other side effects based on the SQL provided. An AI agent given this tool without strict input validation could be manipulated into running destructive queries.

From the tool's own definition: "Tool explicitly described as 'Execute a SQL query against a Metabase database'. The verb 'Execute' combined with 'SQL query' indicates arbitrary code execution capability."

Risk signals: Accepts freeform code/query input (query)

## Use case

AI agents invoke execute_query to trigger actions in Metabase Analytics Integration Server. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Metabase Analytics Integration Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_query": {
      "limits": [
        {
          "counter": "execute_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Metabase Analytics Integration Server (15)

- `delete_dashboard` — Destructive — https://policylayer.com/tools/zsh52013148087-metabase-mcp/delete-dashboard.md
- `execute_card` — Execute — https://policylayer.com/tools/zsh52013148087-metabase-mcp/execute-card.md
- `get_dashboard_cards` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/get-dashboard-cards.md
- `get_table_fields` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/get-table-fields.md
- `list_cards` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/list-cards.md
- `list_collections` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/list-collections.md
- `list_dashboards` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/list-dashboards.md
- `list_databases` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/list-databases.md
- `list_tables` — Read — https://policylayer.com/tools/zsh52013148087-metabase-mcp/list-tables.md
- `add_card_to_dashboard` — Write — https://policylayer.com/tools/zsh52013148087-metabase-mcp/add-card-to-dashboard.md
- `create_card` — Write — https://policylayer.com/tools/zsh52013148087-metabase-mcp/create-card.md
- `create_collection` — Write — https://policylayer.com/tools/zsh52013148087-metabase-mcp/create-collection.md
- `create_dashboard` — Write — https://policylayer.com/tools/zsh52013148087-metabase-mcp/create-dashboard.md
- `update_card_visualization` — Write — https://policylayer.com/tools/zsh52013148087-metabase-mcp/update-card-visualization.md
- `update_dashboard` — Write — https://policylayer.com/tools/zsh52013148087-metabase-mcp/update-dashboard.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=zsh52013148087-metabase-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/zsh52013148087-metabase-mcp