AI agents use create_room to create or update resources in Gomoku — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gomoku environment.
The tool performs a write operation by creating a new game room resource. While this modifies server state, it is fully reversible (rooms can be deleted/left), involves no deletion, execution of arbitrary code, or financial impact. The blast radius of misuse is minimal—at worst, an agent could spam room creation, which is a low-severity issue for a gaming server.
From the tool's definition Tool creates a new game room ("创建游戏房间" = "create game room"), which initializes reversible game state. This is a write operation that generates new data without destructive or financial consequences.
Attacks that exploit this kind of access
创建游戏房间. It is categorised as a Write tool in the Gomoku MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gomoku MCP server in PolicyLayer and add a rule for create_room: 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 Gomoku. Nothing to install.
create_room 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 create_room 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 create_room. 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.
create_room is provided by the Gomoku MCP server (sanshao85/gomoku-ai-battle). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →