execute_multiple_queries · MCP MySQL Server MCP

WHAT IT DOES

What execute_multiple_queries does on MCP MySQL Server

AI agents invoke execute_multiple_queries to trigger actions in MCP MySQL 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 execute_multiple_queries needs a policy

This tool executes arbitrary batches of SQL statements, which can span every risk category: SELECT (read), INSERT/UPDATE (write), DELETE/DROP (destructive), and GRANT (privilege escalation). The most severe applicable category is Execute (potentially Destructive), as an AI agent or attacker could issue DROP TABLE, DELETE FROM, or other irreversible operations.

From the tool's definition "Execute multiple SQL queries separated by semicolons with full transaction control" — arbitrary multi-statement SQL execution including DDL, DML, and DCL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_multiple_queries Rate-limited

execute_multiple_queries 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": {
    "execute_multiple_queries": {
      "limits": [
        {
          "counter": "execute_multiple_queries_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 MySQL Server, so you can run agents against it safely.

FAQ

Questions about execute_multiple_queries

What does the execute_multiple_queries tool do? +

Execute multiple SQL queries separated by semicolons with full transaction control. It is categorised as a Execute tool in the MCP MySQL 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 execute_multiple_queries? +

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

What risk level is execute_multiple_queries? +

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

Can I rate-limit execute_multiple_queries? +

Yes. Add a rate_limit block to the execute_multiple_queries 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_multiple_queries completely? +

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

execute_multiple_queries is provided by the MCP MySQL Server MCP server (kami2k1/mcp-mysql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.