Executes any non-SELECT SQL statement (e.g., ALTER TABLE, DROP, etc.)
AI agents call execute_sql to permanently remove resources in MySQL MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool explicitly executes arbitrary non-SELECT SQL, including DROP statements which irreversibly destroy tables and data. The open-ended 'any non-SELECT SQL' scope means it can perform DROP TABLE, DROP DATABASE, TRUNCATE, and other irreversible destructive operations with no stated safeguards. This is the highest-risk category given the blast radius of potential data destruction.
From the tool's definition Executes any non-SELECT SQL statement (e.g., ALTER TABLE, DROP, etc.)
Documented attack patterns abuse exactly the kind of access execute_sql gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MySQL MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_sql:
{
"version": "1",
"default": "deny",
"hide": [
"execute_sql"
]
}execute_sql disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Executes any non-SELECT SQL statement (e.g., ALTER TABLE, DROP, etc.). It is categorised as a Destructive tool in the MySQL MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MySQL MCP Server 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 MySQL MCP Server. Nothing to install.
execute_sql is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
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.
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.
execute_sql is provided by the MySQL MCP Server MCP server (michael7736/mysql-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MySQL MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MySQL MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.