sql_run · MCP SQL Server MCP: Risk & Policy

WHAT IT DOES

What sql_run does on MCP SQL Server

AI agents invoke sql_run to trigger actions in MCP SQL 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.

WHY IT NEEDS A POLICY

Why sql_run needs a policy

This tool runs arbitrary SQL queries with named parameters. While the server claims 'safety controls against destructive operations,' the tool itself performs Execute-level actions (query execution with runtime effects). It is not Destructive because the server description explicitly notes protections against destructive operations, and sibling tools like sql_describe_table and sql_list_tables are read-only.

From the tool's definition 'sql_run' executes a SQL statement ('Ejecuta una sentencia SQL'); the tool name and description indicate direct code execution with user-supplied SQL arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sql_run Rate-limited

sql_run 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": {
    "sql_run": {
      "limits": [
        {
          "counter": "sql_run_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 MCP SQL Server, so you can run agents against it safely.

FAQ

Questions about sql_run

What does the sql_run tool do? +

Ejecuta una sentencia SQL individual usando parámetros nombrados opcionales. It is categorised as a Execute tool in the MCP SQL Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sql_run? +

Register the MCP SQL Server MCP server in PolicyLayer and add a rule for sql_run: 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 MCP SQL Server. Nothing to install.

What risk level is sql_run? +

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

Can I rate-limit sql_run? +

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

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

sql_run is provided by the MCP SQL Server MCP server (miguel1603/mcp-sql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.