Create game entities from templates - characters, locations, encounters. 🎯 QUICK START: - spawn_character: Single creature from template (goblin, orc, bandit) - spawn_encounter: Full combat from preset or random selection 🏠 LOCATIONS: - spawn_location: Custom populated location with NPCs and ro...
AI agents use spawn_manage to create or update resources in Rpg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rpg environment.
This tool creates and instantiates new game state data (characters, locations, encounters, combat scenarios) in a persistent SQLite database. These are Write operations—reversible modifications that add data to the game world. While the tool has broad scope (can spawn many entity types), it does not execute arbitrary code, delete data, or cause financial impact.
From the tool's definition Tool description states 'Create game entities from templates - characters, locations, encounters' with sub-functions like spawn_character, spawn_encounter, spawn_location, and spawn_tactical that generate new in-game objects from templates.
Documented attack patterns abuse exactly the kind of access spawn_manage gives an agent:
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 spawn_manage:
{
"version": "1",
"default": "deny",
"tools": {
"spawn_manage": {
"limits": [
{
"counter": "spawn_manage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}spawn_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.
Free to start. No card required.
Create game entities from templates - characters, locations, encounters. 🎯 QUICK START: - spawn_character: Single creature from template (goblin, orc, bandit) - spawn_encounter: Full combat from preset or random selection 🏠 LOCATIONS: - spawn_location: Custom populated location with NPCs and rooms - spawn_preset_location: Pre-built location (tavern, dungeon entrance) at world coordinates ⚔️ TACTICAL COMBAT: - spawn_tactical: Custom combat setup with positioned participants and terrain patterns 📋 TEMPLATES: goblin, orc, skeleton, zombie, bandit, wolf, bear, etc. Terrain patterns: arena, canyon, river_valley, mountain_pass, maze 🔄 WORKFLOW: 1. spawn_encounter/spawn_tactical creates combat → Returns encounterId 2. Use combat_action for attacks, combat_map for visualization 3. Use corpse_manage after combat ends Actions: spawn_character, spawn_location, spawn_encounter, spawn_preset_location, spawn_tactical. 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.
Register the Rpg MCP server in PolicyLayer and add a rule for spawn_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.
spawn_manage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the spawn_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.
Set action: deny in the PolicyLayer policy for spawn_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.
spawn_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.
Start from Rpg, 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.
47 Rpg tools catalogued and risk-classified — across an index of 43,000+ MCP servers.