AI agents call closed_orders to retrieve information from Kraken Pro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to fetch closed/completed orders from the Kraken account, which is a read operation with no side effects. While it accesses financial account data (which could inform trading decisions), it does not move money, create, modify, or delete orders—it only retrieves historical information.
From the tool's definition Tool name 'closed_orders' and sibling context indicate this retrieves historical order data. No description provided, but the naming pattern (alongside read-only tools like 'account_balance', 'asset_info', 'ohlc', 'open_orders', 'order_book',…
Documented attack patterns abuse exactly the kind of access closed_orders gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kraken Pro MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for closed_orders:
{
"version": "1",
"default": "deny",
"tools": {
"closed_orders": {}
}
}closed_orders is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
closed_orders. It is categorised as a Read tool in the Kraken Pro MCP MCP Server, which means it retrieves data without modifying state.
Register the Kraken Pro MCP server in PolicyLayer and add a rule for closed_orders: 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 Kraken Pro MCP. Nothing to install.
closed_orders is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the closed_orders 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 closed_orders. 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.
closed_orders is provided by the Kraken Pro MCP server (oilst/kraken-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kraken Pro MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Kraken Pro MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.