AI agents invoke cc_new_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 performs a state-modifying action (resetting a counter) that affects game flow. It is not a simple read operation (no 'get' or 'query'), nor is it destructive (the reset is reversible and part of normal game mechanics). It qualifies as Execute because it triggers state transitions in the game system.
From the tool's definition Tool name and description indicate it 'Reset[s] the action counter to begin a new turn', which modifies game state in a way that triggers or enables subsequent operations.
Attacks that exploit this kind of access
Reset the action counter to begin a new turn. ONLY call this after you have summarized the. 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 cc_new_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.
cc_new_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 cc_new_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 cc_new_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.
cc_new_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 →