AI agents call get_stock_realtime to retrieve information from Stock-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves real-time stock market data without side effects. It is a read-only query operation that returns market information (prices, volumes, etc.) for Chinese stock exchanges. There is no capability to execute trades, modify data, delete records, or commit financial obligations. The worst-case misuse would be information disclosure, which has low blast radius.
From the tool's definition Tool name 'get_stock_realtime' and description '获取A股全部实时行情数据' (get all A-share real-time market data) indicate data retrieval only. No modification, execution, deletion, or financial transaction capability.
Attacks that exploit this kind of access
获取A股全部实时行情数据. It is categorised as a Read tool in the Stock-MCP MCP Server, which means it retrieves data without modifying state.
Register the Stock- MCP server in PolicyLayer and add a rule for get_stock_realtime: 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 Stock-MCP. Nothing to install.
get_stock_realtime 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_realtime 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_realtime. 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_realtime is provided by the Stock- MCP server (nomi982/stock-mcp). 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 →