AI agents call pionex.orders.get_order to retrieve information from Pionex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_order' naming convention strongly implies a read/fetch operation to retrieve a specific order by ID. Sibling tools follow clear naming patterns (get_balance, get_depth, get_trades, get_open_orders) all being reads, and 'get_order' fits this pattern. However, the empty description lowers confidence. Severity is medium because it accesses potentially sensitive financial order data on a trading platform.
From the tool's definition Tool name 'get_order' suggests retrieval of order data; description is empty and uninformative.
Attacks that exploit this kind of access
pionex.orders.get_order. It is categorised as a Read tool in the Pionex MCP Server, which means it retrieves data without modifying state.
Register the Pionex MCP server in PolicyLayer and add a rule for pionex.orders.get_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 Pionex. Nothing to install.
pionex.orders.get_order 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 pionex.orders.get_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 pionex.orders.get_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.
pionex.orders.get_order is provided by the Pionex MCP server (pionex-mcp-server). 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 →