AI agents call get_user_security_group 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 tool only retrieves metadata about how the user has organized their watchlist groups. It performs a read-only query with no side effects, data modification, code execution, or financial impact. The blast radius of misuse is minimal—an attacker gains visibility into the user's portfolio organization but cannot execute trades, access sensitive account details beyond grouping structure, or cause harm.
From the tool's definition Tool name 'get_user_security_group' and description '获取自选股分组列表，查看所有可用的自选股分组' (Get watchlist group list, view all available watchlist groups) indicate a retrieval operation that queries user's watchlist organization without modification.
Documented attack patterns abuse exactly the kind of access get_user_security_group 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_user_security_group:
{
"version": "1",
"default": "deny",
"tools": {
"get_user_security_group": {}
}
}get_user_security_group 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.
获取自选股分组列表，查看所有可用的自选股分组. 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_user_security_group: 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_user_security_group 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_user_security_group 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_user_security_group. 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_user_security_group 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.