Grand strategy nation management for multi-agent games. 🏰 NATION SETUP: 1. create_nation - Define nation with ideology, traits, resources 2. get_state - Query nation state (public/private/fog_of_war view) 3. list_nations - See all nations in world 🎭 NATION TRAITS: - ideology: democracy | autocr...
AI agents use strategy_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 entities (nations, alliances, diplomatic relationships) within a persistent SQLite-backed game engine. These are reversible writes to game state. The most severe sub-action visible is creating nations and proposing alliances, which are Write-level operations. No irreversible deletion, code execution, or financial transactions are indicated.
From the tool's definition Grand strategy nation management for multi-agent games; create_nation, propose_alliance, get_state, list_nations — creates and modifies nation states, diplomacy, and resources
Documented attack patterns abuse exactly the kind of access strategy_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 strategy_manage:
{
"version": "1",
"default": "deny",
"tools": {
"strategy_manage": {
"limits": [
{
"counter": "strategy_manage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}strategy_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.
Grand strategy nation management for multi-agent games. 🏰 NATION SETUP: 1. create_nation - Define nation with ideology, traits, resources 2. get_state - Query nation state (public/private/fog_of_war view) 3. list_nations - See all nations in world 🎭 NATION TRAITS: - ideology: democracy | autocracy | theocracy | tribal - aggression: 0-100 (affects AI behavior) - trust: 0-100 (alliance reliability) - paranoia: 0-100 (defensive posture) 💰 STARTING RESOURCES: - food: Population growth - metal: Military production - oil: Advanced units/vehicles 🤝 DIPLOMACY: - propose_alliance: Offer pact to another nation - claim_region: Assert territorial expansion ⚔️ TURN RESOLUTION: Use turn_manage for turn lifecycle. resolve_turn processes: - Resource production - Territory conflicts - Alliance effects Actions: create_nation, get_state, propose_alliance, claim_region, resolve_turn, list_nations. 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 strategy_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.
strategy_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 strategy_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 strategy_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.
strategy_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.