Release a creature from your party. This cannot be undone.
AI agents call cc_release to permanently remove resources in Ttt — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although this tool operates within a game context (creature collection mechanics), the description unambiguously states the action is irreversible. Release operations that permanently remove game assets from a player's inventory or party are destructive by definition.
From the tool's definition "Release a creature from your party. This cannot be undone." The phrase "cannot be undone" explicitly indicates an irreversible operation that destroys or permanently removes data (a creature from the player's party).
Attacks that exploit this kind of access
Release a creature from your party. This cannot be undone. It is categorised as a Destructive tool in the Ttt MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ttt MCP server in PolicyLayer and add a rule for cc_release: 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_release is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cc_release 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_release. 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_release 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 →