exec_sql · Code Box MCP: Risk & Policy

WHAT IT DOES

What exec_sql does on Code Box

AI agents invoke exec_sql to trigger actions in Code Box. 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 exec_sql needs a policy

The name 'exec_sql' strongly implies executing arbitrary SQL queries. Given the server context (stateful code execution, file I/O, artifact management), this tool likely runs SQL against a database. Arbitrary SQL execution can include destructive operations (DROP, DELETE, TRUNCATE), making this at minimum Execute and potentially Destructive.

From the tool's definition Tool name 'exec_sql' on a server that explicitly offers 'SQL query support'; sibling tool 'exec_code' confirms execution-oriented design; description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec_sql Rate-limited

exec_sql 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": {
    "exec_sql": {
      "limits": [
        {
          "counter": "exec_sql_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 Code Box, so you can run agents against it safely.

FAQ

Questions about exec_sql

What does the exec_sql tool do? +

exec_sql. It is categorised as a Execute tool in the Code Box MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on exec_sql? +

Register the Code Box MCP server in PolicyLayer and add a rule for exec_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 Code Box. Nothing to install.

What risk level is exec_sql? +

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

Can I rate-limit exec_sql? +

Yes. Add a rate_limit block to the exec_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.

How do I block exec_sql completely? +

Set action: deny in the PolicyLayer policy for exec_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.

What MCP server provides exec_sql? +

exec_sql is provided by the Code Box MCP server (madhanmohanreddy2301/codeboxmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.