execute_sql

THE RISK

High Risk

Why execute_sql needs a policy

SQL execution is a classic Execute category risk: it runs code whose effects depend on the query argument. While a sibling tool 'delete_dataset' is Destructive, this tool itself permits both read and write operations (SELECT, INSERT, UPDATE, DELETE, DROP) depending on the SQL provided.

From the tool's definition Tool name is 'execute_sql' and description states it 'Execute[s] SQL query using /api/v1/sqllab/execute/ endpoint'. This directly executes arbitrary SQL code.

Documented attack patterns abuse exactly the kind of access execute_sql gives an agent:

POLICY

How to control execute_sql

PolicyLayer is an MCP gateway — it sits between your AI agents and Superset, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_sql:

policy.json

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

execute_sql 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.

Create a free account and register Superset — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Superset tools

Destructive delete_calculated_column Delete one or more calculated columns from a dataset Destructive delete_dataset Deletes a dataset from Superset. This is a permanent operation and cannot be undone. Be ca Destructive delete_dataset_metric Delete one or more metrics from a dataset Destructive remove_chart_from_dashboard Remove a chart from a dashboard and clean up its layout nodes. Execute refresh_dataset_schema Refreshes a dataset Write set_chart_filters Set data filters for a chart. This permanently updates the chart Write find_and_replace_in_sql Performs a simple text find-and-replace on a virtual dataset Write add_chart_to_dashboard Add an existing chart to a dashboard and place it in the layout (position_json).

All 31 Superset tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Superset → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about execute_sql

What does the execute_sql tool do? +

Execute SQL query using /api/v1/sqllab/execute/ endpoint. It is categorised as a Execute tool in the Superset 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_sql? +

Register the Superset MCP server in PolicyLayer and add a rule for execute_sql: 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 Superset. Nothing to install.

What risk level is execute_sql? +

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

Can I rate-limit execute_sql? +

Yes. Add a rate_limit block to the execute_sql 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_sql completely? +

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

execute_sql is provided by the Superset MCP server (winding2020/superset-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Superset tool call.

Start from Superset, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →