run_sql_query

THE RISK

Low Risk

Why run_sql_query needs a policy

The tool is explicitly described as read-only and limited to SELECT statements, meaning it retrieves data without side effects. However, severity is medium because unrestricted SELECT access can expose sensitive data across the entire database, and the enforcement of the read-only constraint depends on the implementation.

From the tool's definition Executes a read-only SQL query (SELECT statements only) against the MySQL database.

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

POLICY

How to control run_sql_query

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 run_sql_query:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_sql_query": {}
  }
}

run_sql_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

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

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MySQL MCP Server tools

Destructive delete_data Deletes data from a table in the MySQL database. Destructive execute_sql Executes any non-SELECT SQL statement (e.g., ALTER TABLE, DROP, etc.) Write create_table Creates a new table in the MySQL database. Write insert_data Inserts data into a table in the MySQL database. Write update_data Updates data in a table in the MySQL database.

All 6 MySQL MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_sql_query

What does the run_sql_query tool do? +

Executes a read-only SQL query (SELECT statements only) against the MySQL database. It is categorised as a Read tool in the MySQL MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on run_sql_query? +

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

What risk level is run_sql_query? +

run_sql_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit run_sql_query? +

Yes. Add a rate_limit block to the run_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 run_sql_query completely? +

Set action: deny in the PolicyLayer policy for run_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 run_sql_query? +

run_sql_query 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.

Enforce policy on every MySQL MCP Server tool call.

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.

CHECK YOUR STACK →