AI agents use ot_buy to commit financial operations through Ttt — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool commits financial transactions by purchasing goods at defined prices. Even if simulated within a game context (Oregon Trail-style), the tool explicitly involves spending currency/money, placing it in the Financial category. Severity is high because an AI agent could repeatedly purchase items, draining in-game resources irreversibly.
From the tool's definition 'Buy supplies' with explicit prices: food=$2/day, medicine=$6/dose, ammo=$1/round, parts=$10, oxen=$20
Attacks that exploit this kind of access
Buy supplies at a trading post or fort. Only available at stops where trading is possible. Prices: food=$2/day, medicine=$6/dose, ammo=$1/round, parts=$10, oxen=$20. It is categorised as a Financial tool in the Ttt MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Ttt MCP server in PolicyLayer and add a rule for ot_buy: 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_buy is a Financial 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 ot_buy 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_buy. 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_buy 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 →