Medium Risk

create_random_table

Create a new random table for encounters, loot, weather, etc.

How to control create_random_table ↓

What create_random_table does on DMCP

AI agents use create_random_table to create or update resources in DMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DMCP environment.

Medium Risk

Why create_random_table needs a policy

This tool creates or modifies game state by adding new random tables, which is a reversible write operation. It has no destructive capability (tables can be replaced or removed), does not execute external code or shell commands, and does not affect real-world systems or finances. The blast radius is confined to the RPG game context and is easily undoable, making it low severity.

From the tool's definition The tool 'create_random_table' creates a new random table, which is a data creation operation. The description states it creates tables for encounters, loot, weather, etc., indicating it persists new structured data within the game state.

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

How to control create_random_table

PolicyLayer is an MCP gateway — it sits between your AI agents and DMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_random_table:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_random_table": {
      "limits": [
        {
          "counter": "create_random_table_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_random_table 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.

  1. Create a free account and register DMCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_random_table

What does the create_random_table tool do? +

Create a new random table for encounters, loot, weather, etc. It is categorised as a Write tool in the DMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_random_table? +

Register the D MCP server in PolicyLayer and add a rule for create_random_table: 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 DMCP. Nothing to install.

What risk level is create_random_table? +

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

Can I rate-limit create_random_table? +

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

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

create_random_table is provided by the D MCP server (shawnrushefsky/dmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every DMCP tool call.

Start from DMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

204 DMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.