# new_game

Start a new chess game from the standard initial position.

Agent View of the PolicyLayer registry record for `new_game`. HTML page: https://policylayer.com/tools/11hritik11-chess-mcp/new-game

## Facts

- Tool: `new_game`
- Server: Chess MCP Server (`11hritik11/chess-mcp`) — https://policylayer.com/tools/11hritik11-chess-mcp.md
- Homepage: https://github.com/11hritik11/chess-mcp
- Risk category: Execute (High risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "new_game",
    "arguments": {}
  }
}
```

## Why new_game is rated High

This tool executes a chess game initialization via the Stockfish engine. While benign in isolation, it qualifies as Execute rather than Read because it triggers external operations and state changes in the chess engine, not merely retrieving data. Severity is low because chess game initiation has no harmful blast radius—no data is deleted, overwritten, or financial impact occurs.

From the tool's own definition: "Tool initiates a new chess game, which triggers an external operation (Stockfish engine interaction) whose effects depend on game state arguments. Described as 'Start a new chess game' - an action that executes game logic."

## Use case

AI agents invoke new_game to trigger actions in Chess MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Chess MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "new_game": {
      "limits": [
        {
          "counter": "new_game_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Chess MCP Server (2)

- `engine_move` — Execute — https://policylayer.com/tools/11hritik11-chess-mcp/engine-move.md
- `make_move` — Write — https://policylayer.com/tools/11hritik11-chess-mcp/make-move.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=11hritik11-chess-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/11hritik11-chess-mcp