scene_manage

THE RISK

Medium Risk

Why scene_manage needs a policy

This tool modifies shared scene state that other players/agents depend on within the RPG session. While not destructive (scenes can presumably be reset or modified further), it is clearly Write-category because it creates or modifies persistent game data. The severity is medium because misuse could corrupt an active game session's consistency, but the blast radius is limited to a single game instance.

From the tool's definition Tool name 'scene_manage' combined with description 'Manage DM-committed shared scenes — the engine-side source of truth for' indicates modification of shared game state data.

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

POLICY

How to control scene_manage

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

policy.json

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

scene_manage 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.

Create a free account and register Rpg — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Rpg tools

Execute improvisation_manage Manage improvised actions, custom effects, and arcane synthesis. Actions: stunt, apply_eff Execute execute_lair_action Execute a lair action at initiative 20 when isLairActionPending is true. Apply environment Execute concentration_manage Manage spell concentration (D&D 5e rules). 🎯 WHEN TO USE: - After damage: check_save (CO Execute roll_death_save Roll a d20 death saving throw for a character at 0 HP. 10+ success, nat 20 regains 1 HP, n Execute turn_manage Turn-based strategy game lifecycle (multi-agent coordination). 🎮 STRATEGY TURN CYCLE: 1. Write world_map World map operations - viewing, rendering, and modification. Actions: overview, region, ti Write advance_turn Advance to the next combatant\ Write agent_manage Manage LLM-driven NPCs (

All 47 Rpg tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about scene_manage

What does the scene_manage tool do? +

Manage DM-committed shared scenes — the engine-side source of truth for. It is categorised as a Write tool in the Rpg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on scene_manage? +

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

What risk level is scene_manage? +

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

Can I rate-limit scene_manage? +

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

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

scene_manage is provided by the Rpg MCP server (mnehmos/mnehmos.rpg.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Rpg tool call.

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

CHECK YOUR STACK →