execute_select_statement · Mcp Ohmy Sql MCP: Risk & Policy

WHAT IT DOES

What execute_select_statement does on Mcp Ohmy Sql

AI agents invoke execute_select_statement to trigger actions in Mcp Ohmy Sql. 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_select_statement needs a policy

Although SELECT statements are typically read-only, this tool executes arbitrary SQL queries, which falls under the Execute category. It has high severity because: (1) a poorly crafted or malicious SELECT could access sensitive data across the database, (2) SELECT statements can include side effects (e.g., triggers, user-defined functions), (3) an AI agent could be tricked into executing resource-intensive queries…

From the tool's definition Tool name is 'execute_select_statement' which directly indicates SQL statement execution. Server description explicitly states it 'bridges AI assistants with SQL databases, enabling natural language querying.' The tool description is empty, but the name and…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_select_statement Rate-limited

execute_select_statement 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_select_statement": {
      "limits": [
        {
          "counter": "execute_select_statement_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 Ohmy Sql, so you can run agents against it safely.

FAQ

Questions about execute_select_statement

What does the execute_select_statement tool do? +

execute_select_statement. It is categorised as a Execute tool in the Mcp Ohmy Sql 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_select_statement? +

Register the Mcp Ohmy Sql MCP server in PolicyLayer and add a rule for execute_select_statement: 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 Ohmy Sql. Nothing to install.

What risk level is execute_select_statement? +

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

Can I rate-limit execute_select_statement? +

Yes. Add a rate_limit block to the execute_select_statement 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_select_statement completely? +

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

execute_select_statement is provided by the Mcp Ohmy Sql MCP server (machu-gwu/mcp_ohmy_sql-project). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.