获取单个股票的历史数据、过去价格、K线数据，支持日K、周K、月K线，用于分析股票过去的表现
AI agents call get-stock-history to retrieve information from MCP Stock Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical stock price data and technical indicators (K-line/candlestick data) for analysis purposes. It has no side effects, does not modify data, execute code, delete information, or commit financial transactions. It is a pure read operation that fetches pre-existing historical market information from the Xueqiu API.
From the tool's definition Tool name 'get-stock-history' and description '获取单个股票的历史数据、过去价格、K线数据' (fetch historical data, past prices, candlestick data) indicate retrieval of historical market data with no modification or execution capabilities.
Attacks that exploit this kind of access
获取单个股票的历史数据、过去价格、K线数据，支持日K、周K、月K线，用于分析股票过去的表现. It is categorised as a Read tool in the MCP Stock Assistant MCP Server, which means it retrieves data without modifying state.
Register the MCP Stock Assistant MCP server in PolicyLayer and add a rule for get-stock-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 MCP Stock Assistant. Nothing to install.
get-stock-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 get-stock-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 get-stock-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.
get-stock-history is provided by the MCP Stock Assistant MCP server (qqzhangyanhua/mcp-stock). 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 →