AI agents call get_positions to retrieve information from 富途 MCP 服务器 (Futu MCP Server) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it queries financial position data from the Futu API. However, the severity is high because it exposes sensitive financial information about user holdings and positions, which could be exploited if an AI agent is compromised or manipulated into leaking this data to unauthorized parties.
From the tool's definition Tool name is 'get_positions' which retrieves (获取) position information. The description states it requires trading permissions (需要交易权限) but only retrieves/queries data without modifying it. No side effects occur from calling this tool.
Documented attack patterns abuse exactly the kind of access get_positions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 富途 MCP 服务器 (Futu MCP Server), and nothing reaches the server without passing your rules. This is the rule we recommend for get_positions:
{
"version": "1",
"default": "deny",
"tools": {
"get_positions": {}
}
} get_positions 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.
获取持仓信息(需要交易权限). It is categorised as a Read tool in the 富途 MCP 服务器 (Futu MCP Server) MCP Server, which means it retrieves data without modifying state.
Register the 富途 MCP 服务器 (Futu MCP Server) MCP server in PolicyLayer and add a rule for get_positions: 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 富途 MCP 服务器 (Futu MCP Server). Nothing to install.
get_positions 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 get_positions 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 get_positions. 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.
get_positions is provided by the 富途 MCP 服务器 (Futu MCP Server) MCP server (shuchaang/futu-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 富途 MCP 服务器 (Futu MCP Server), 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.
10 富途 MCP 服务器 (Futu MCP Server) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.