The Flufflings catch their breath and check in with the player. Resets the step counter and gives 8 fresh steps. Must be called after reaching the turn limit — chat first, then call this to continue the crossing.
AI agents invoke ms_next_turn to trigger actions in Ttt. 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.
This tool executes a game state transition (reset counter, allocate steps) contingent on game conditions. While not destructive or irreversible, it operates a stateful game system and advances turn progression — characteristic of Execute category. The low severity reflects that impacts are confined to a game context with no external effects, data loss, or financial consequences.
From the tool's definition Tool description states it 'Resets the step counter and gives 8 fresh steps' and 'Must be called after reaching the turn limit' — these are procedural state-management actions that trigger in-game logic progression.
Attacks that exploit this kind of access
The Flufflings catch their breath and check in with the player. Resets the step counter and gives 8 fresh steps. Must be called after reaching the turn limit — chat first, then call this to continue the crossing. It is categorised as a Execute tool in the Ttt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ttt MCP server in PolicyLayer and add a rule for ms_next_turn: 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 Ttt. Nothing to install.
ms_next_turn is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ms_next_turn 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 ms_next_turn. 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.
ms_next_turn is provided by the Ttt MCP server (srmtech-git/mcparcade). 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 →