Choose how to cross the current river. Ford=fast but risky. Caulk=float the wagon, medium risk. Ferry=safe but costs $15. Wait=lose 2 days and food but calmer water. Narrate the crossing dramatically.
AI agents invoke ot_cross_river 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 action that advances state and produces consequences (time loss, food consumption, cost, risk outcomes). While framed as a narrative game choice, it is fundamentally an Execute action because it runs a sequence whose side effects (resource depletion, progress, danger) depend entirely on the argument passed.
From the tool's definition Tool triggers external operations ('cross the current river', 'caulk', 'ford', 'ferry', 'wait') whose outcomes depend on the chosen argument. The narration and game state effects are contingent on the decision made.
Attacks that exploit this kind of access
Choose how to cross the current river. Ford=fast but risky. Caulk=float the wagon, medium risk. Ferry=safe but costs $15. Wait=lose 2 days and food but calmer water. Narrate the crossing dramatically. 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 ot_cross_river: 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.
ot_cross_river 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 ot_cross_river 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 ot_cross_river. 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.
ot_cross_river 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 →