Atomic amend in-place (keeps identifiers & queue priority where possible).
AI agents use amend_order to commit financial operations through Kraken Pro MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Amending an order on a financial trading platform directly modifies a live trading order, which constitutes a financial operation. Misuse could alter price, quantity, or direction of trades, resulting in unintended financial exposure or losses. The 'atomic amend in-place' language confirms this modifies real exchange orders.
From the tool's definition amend_order on a trading platform (Kraken Pro) that atomically amends in-place an existing order — modifying live financial orders on an exchange
Documented attack patterns abuse exactly the kind of access amend_order 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 amend_order:
{
"version": "1",
"default": "deny",
"tools": {
"amend_order": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to amend_order is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Atomic amend in-place (keeps identifiers & queue priority where possible). It is categorised as a Financial tool in the Kraken Pro MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Kraken Pro MCP server in PolicyLayer and add a rule for amend_order: 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.
amend_order 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 amend_order 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 amend_order. 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.
amend_order 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.