json_to_ddl · Claude MCP Data Engineer Server MCP

WHAT IT DOES

What json_to_ddl does on Claude MCP Data Engineer Server

AI agents use json_to_ddl to create or update resources in Claude MCP Data Engineer Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude MCP Data Engineer Server environment.

WHY IT NEEDS A POLICY

Why json_to_ddl needs a policy

This tool creates database schema objects (tables) through DDL statements, which is a reversible write operation. While tables can be dropped, the primary action is creation/modification of schema, not destruction. The severity is medium because misuse could create unwanted tables consuming resources, but the effect is reversible via DROP TABLE. It does not execute arbitrary code or cause irreversible data loss.

From the tool's definition Tool generates a CREATE TABLE SQL DDL statement, which creates a new table structure in a database. The verb 'Generate' combined with 'CREATE TABLE' indicates data structure creation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

json_to_ddl Rate-limited

json_to_ddl stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "json_to_ddl": {
      "limits": [
        {
          "counter": "json_to_ddl_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude MCP Data Engineer Server, so you can run agents against it safely.

FAQ

Questions about json_to_ddl

What does the json_to_ddl tool do? +

Generate a CREATE TABLE SQL DDL statement from a JSON sample record. It is categorised as a Write tool in the Claude MCP Data Engineer Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on json_to_ddl? +

Register the Claude MCP Data Engineer Server MCP server in PolicyLayer and add a rule for json_to_ddl: 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 Claude MCP Data Engineer Server. Nothing to install.

What risk level is json_to_ddl? +

json_to_ddl is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit json_to_ddl? +

Yes. Add a rate_limit block to the json_to_ddl 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 json_to_ddl completely? +

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

json_to_ddl is provided by the Claude MCP Data Engineer Server MCP server (itsnikhile/claude-mcp-data-engineer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.