# execute_query

Execute a SQL query (SELECT statements only)

Agent View of the PolicyLayer registry record for `execute_query`. HTML page: https://policylayer.com/tools/1luvc0d3-metabase-mcp/execute-query

## Facts

- Tool: `execute_query`
- Server: Metabase MCP (`1luvc0d3/metabase-mcp`) — https://policylayer.com/tools/1luvc0d3-metabase-mcp.md
- Homepage: https://github.com/1luvc0d3/metabase-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## 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

The tool's primary action is to execute code (SQL queries) whose effects depend on the arguments provided. Although the restriction to SELECT statements prevents destructive operations (DELETE, DROP), the ability to execute arbitrary SELECT queries remains an Execute-category risk: an AI agent could craft expensive queries, access sensitive data across tables, or trigger application-side effects.

From the tool's own definition: "Tool description explicitly states it 'Execute[s] a SQL query' and calls the operation 'execute'. While constrained to SELECT statements only (mitigating destructive risk), execution of arbitrary read queries against a database constitutes code execution with…"

## Use case

AI agents invoke execute_query 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.

## Recommended policy (PolicyLayer)

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

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

## Other tools on Metabase MCP (29)

- `delete_card` — Destructive — https://policylayer.com/tools/1luvc0d3-metabase-mcp/delete-card.md
- `delete_dashboard` — Destructive — https://policylayer.com/tools/1luvc0d3-metabase-mcp/delete-dashboard.md
- `remove_card_from_dashboard` — Destructive — https://policylayer.com/tools/1luvc0d3-metabase-mcp/remove-card-from-dashboard.md
- `ask_data` — Execute — https://policylayer.com/tools/1luvc0d3-metabase-mcp/ask-data.md
- `batch_execute` — Execute — https://policylayer.com/tools/1luvc0d3-metabase-mcp/batch-execute.md
- `execute_card` — Execute — https://policylayer.com/tools/1luvc0d3-metabase-mcp/execute-card.md
- `nlq_to_sql` — Execute — https://policylayer.com/tools/1luvc0d3-metabase-mcp/nlq-to-sql.md
- `run_workflow` — Execute — https://policylayer.com/tools/1luvc0d3-metabase-mcp/run-workflow.md
- `compare_metrics` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/compare-metrics.md
- `explain_sql` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/explain-sql.md
- `generate_insights` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/generate-insights.md
- `get_card` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/get-card.md
- `get_collections` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/get-collections.md
- `get_dashboard` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/get-dashboard.md
- `get_database_schema` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/get-database-schema.md
- `list_cards` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/list-cards.md
- `list_dashboards` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/list-dashboards.md
- `list_databases` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/list-databases.md
- `optimize_sql` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/optimize-sql.md
- `search_content` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/search-content.md
- `trend_analysis` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/trend-analysis.md
- `validate_sql` — Read — https://policylayer.com/tools/1luvc0d3-metabase-mcp/validate-sql.md
- `add_card_to_dashboard` — Write — https://policylayer.com/tools/1luvc0d3-metabase-mcp/add-card-to-dashboard.md
- `create_card` — Write — https://policylayer.com/tools/1luvc0d3-metabase-mcp/create-card.md
- `create_collection` — Write — https://policylayer.com/tools/1luvc0d3-metabase-mcp/create-collection.md
- `create_dashboard` — Write — https://policylayer.com/tools/1luvc0d3-metabase-mcp/create-dashboard.md
- `move_to_collection` — Write — https://policylayer.com/tools/1luvc0d3-metabase-mcp/move-to-collection.md
- `update_card` — Write — https://policylayer.com/tools/1luvc0d3-metabase-mcp/update-card.md
- `update_dashboard` — Write — https://policylayer.com/tools/1luvc0d3-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=1luvc0d3-metabase-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1luvc0d3-metabase-mcp