Manage spatial graph - rooms, exits, and character locations. Actions: look, generate, update, get_exits, move, list, network_create, network_get, network_list Aliases: observe→look, create→generate, edit→update, exits→get_exits, enter→move, rooms→list, networks→network_list 🏠 SPATIAL WORKFLOW: ...
AI agents use spatial_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.
The tool primarily creates and modifies game world data (rooms, networks, character locations) in a SQLite-backed persistent store. Actions like 'generate', 'update', 'network_create', and 'move' write or modify data. The 'look'/'list'/'get_exits' actions are read-only, but the most severe applicable category across all actions is Write (creates/modifies rooms and spatial graphs reversibly).
From the tool's definition Manage spatial graph - rooms, exits, and character locations. Actions: look, generate, update, get_exits, move, list, network_create, network_get, network_list
Documented attack patterns abuse exactly the kind of access spatial_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 spatial_manage:
{
"version": "1",
"default": "deny",
"tools": {
"spatial_manage": {
"limits": [
{
"counter": "spatial_manage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}spatial_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.
Manage spatial graph - rooms, exits, and character locations. Actions: look, generate, update, get_exits, move, list, network_create, network_get, network_list Aliases: observe→look, create→generate, edit→update, exits→get_exits, enter→move, rooms→list, networks→network_list 🏠 SPATIAL WORKFLOW: 1. network_create - Create a spatial network for a town, dungeon, road, or region 2. generate - Create a new room with description, atmospherics, and optional local coordinates 3. update - Patch room description, biome, or atmospherics 4. look - View room from character. 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 spatial_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.
spatial_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 spatial_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 spatial_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.
spatial_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.