AI agents call spot_batch_amend to retrieve information from Okx Trade without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
orders | array | Yes | Array (max 20): {instId, ordId?, clOrdId?, newSz?, newPx?} |
Parameters from the server's own tool schema.
Even though spot_batch_amend only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
[CAUTION] Batch amend up to 20 unfilled spot orders. It is categorised as a Read tool in the Okx Trade MCP Server, which means it retrieves data without modifying state.
spot_batch_amend accepts 1 parameter: orders. Required: orders. The full parameter table on this page comes from the server's own tool schema.
Register the Okx Trade MCP server in PolicyLayer and add a rule for spot_batch_amend: 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 Okx Trade. Nothing to install.
spot_batch_amend 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 spot_batch_amend 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 spot_batch_amend. 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.
spot_batch_amend is provided by the Okx Trade MCP server (@okx_ai/okx-trade-mcp). 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 →