execute_sql_file · Dm MCP: Risk & Policy

WHAT IT DOES

What execute_sql_file does on Dm

AI agents invoke execute_sql_file to trigger actions in Dm. 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_sql_file needs a policy

This tool executes SQL from files, which is fundamentally an Execute operation—it triggers external database operations whose outcomes depend entirely on the SQL code being executed. While SQL files could theoretically contain only SELECT statements (Read) or DELETE statements (Destructive), the tool's design permits arbitrary SQL execution.

From the tool's definition Tool description states '读取并执行 SQL 文件' (read and execute SQL file). The sibling tool 'execute_sql' combined with file execution capability means this can run arbitrary SQL commands whose effects depend on file contents.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_sql_file Rate-limited

execute_sql_file 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_sql_file": {
      "limits": [
        {
          "counter": "execute_sql_file_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 Dm, so you can run agents against it safely.

FAQ

Questions about execute_sql_file

What does the execute_sql_file tool do? +

读取并执行 SQL 文件，用于处理超长 SQL。. It is categorised as a Execute tool in the Dm 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_sql_file? +

Register the Dm MCP server in PolicyLayer and add a rule for execute_sql_file: 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 Dm. Nothing to install.

What risk level is execute_sql_file? +

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

Can I rate-limit execute_sql_file? +

Yes. Add a rate_limit block to the execute_sql_file 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_sql_file completely? +

Set action: deny in the PolicyLayer policy for execute_sql_file. 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_sql_file? +

execute_sql_file is provided by the Dm MCP server (tgich/dm_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.