AI agents call capital_history to retrieve information from Xueqiu MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical financial flow data from the Xueqiu stock market API. It performs a simple data retrieval without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an AI agent could only access or query historical capital flow information, which causes no harm or unintended consequences. This is a standard Read operation.
From the tool's definition Tool description states '获取历史资金流如流出数据，每日数据' (retrieve historical capital flow inflow/outflow data, daily data). The verb '获取' (retrieve/get) indicates a read-only query operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access capital_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xueqiu MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for capital_history:
{
"version": "1",
"default": "deny",
"tools": {
"capital_history": {}
}
}capital_history 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.
获取历史资金流如流出数据，每日数据. It is categorised as a Read tool in the Xueqiu MCP MCP Server, which means it retrieves data without modifying state.
Register the Xueqiu MCP server in PolicyLayer and add a rule for capital_history: 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 Xueqiu MCP. Nothing to install.
capital_history 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 capital_history 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 capital_history. 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.
capital_history is provided by the Xueqiu MCP server (liqiongyu/xueqiu_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xueqiu 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.
45 Xueqiu MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.