AI agents call tiger_get_orders to retrieve information from Tiger MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix strongly indicates a read-only query operation that retrieves order data from the brokerage. No side effects or state modifications are implied. While the description is uninformative, the tool name and sibling patterns support Read classification. Severity is low because reading order history poses minimal direct risk, though confidence is moderate (0.7) due to the missing description.
From the tool's definition Tool name 'tiger_get_orders' indicates a retrieval operation. Description is empty, but the naming pattern (get_*) and context among sibling tools (which include cancel_order, get_account_info, get_market_data) suggests this retrieves existing order…
Documented attack patterns abuse exactly the kind of access tiger_get_orders gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tiger MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for tiger_get_orders:
{
"version": "1",
"default": "deny",
"tools": {
"tiger_get_orders": {}
}
}tiger_get_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.
tiger_get_orders. It is categorised as a Read tool in the Tiger MCP MCP Server, which means it retrieves data without modifying state.
Register the Tiger MCP server in PolicyLayer and add a rule for tiger_get_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 Tiger MCP. Nothing to install.
tiger_get_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 tiger_get_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 tiger_get_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.
tiger_get_orders is provided by the Tiger MCP server (luxiaolei/tiger-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tiger 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.
23 Tiger MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.