High Risk →

sql_query

Execute SQL queries

How to control sql_query ↓

What sql_query does on MCP MySQL Server

AI agents invoke sql_query 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.

High Risk

Why sql_query needs a policy

A tool that executes arbitrary SQL queries can perform any database operation including SELECT (Read), INSERT/UPDATE (Write), DELETE/DROP/TRUNCATE (Destructive), or stored procedure calls (Execute). Since the server explicitly advertises DDL support, the blast radius is maximal — an AI agent could irreversibly destroy schema or data.

From the tool's definition Tool name 'sql_query' and description 'Execute SQL queries' — the word 'Execute' directly indicates running arbitrary SQL. Server description mentions 'DDL support', meaning DROP/DELETE/TRUNCATE are possible.

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

How to control sql_query

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "sql_query": {
      "limits": [
        {
          "counter": "sql_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

sql_query 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.

  1. Create a free account and register MCP MySQL Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about sql_query

What does the sql_query tool do? +

Execute SQL queries. 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 sql_query? +

Register the MCP MySQL Server MCP server in PolicyLayer and add a rule for sql_query: 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 sql_query? +

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

Can I rate-limit sql_query? +

Yes. Add a rate_limit block to the sql_query 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_query completely? +

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

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

Enforce policy on every MCP MySQL Server tool call.

Start from MCP MySQL 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.

5 MCP MySQL Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.