Starts a new game, resetting the board to the initial position.
AI agents use new_game to create or update resources in MCP Chess Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Chess Server environment.
This tool modifies application state by resetting the chess board to its initial position. It is reversible in the sense that no data is permanently deleted — a new game can always be started again. It creates/reinitializes a game session, fitting the Write category. The blast radius is low since it only affects an in-memory chess game state.
From the tool's definition Starts a new game, resetting the board to the initial position.
Documented attack patterns abuse exactly the kind of access new_game gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Chess Server, and nothing reaches the server without passing your rules. This is the rule we recommend for new_game:
{
"version": "1",
"default": "deny",
"tools": {
"new_game": {
"limits": [
{
"counter": "new_game_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}new_game 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.
Starts a new game, resetting the board to the initial position. It is categorised as a Write tool in the MCP Chess Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Chess Server MCP server in PolicyLayer and add a rule for new_game: 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 MCP Chess Server. Nothing to install.
new_game 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 new_game 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 new_game. 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.
new_game is provided by the MCP Chess Server MCP server (jiayao/mcp-chess). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Chess Server, 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.
6 MCP Chess Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.