AI agents call get_realtime_quote to retrieve information from Sfc Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely queries and returns financial market data without modifying, executing operations, or committing any financial transactions. It is a passive data retrieval operation typical of market data APIs. The low severity reflects that misuse (e.g., automated excessive queries) poses minimal security risk compared to tools that write, execute, or transfer funds.
From the tool's definition Tool name 'get_realtime_quote' and description state it retrieves real-time stock quotes including current price, price change percentage, trading volume, transaction amount, turnover rate—all read-only market data queries with no side effects.
Attacks that exploit this kind of access
获取A股股票实时行情（当前价、涨跌幅、成交量、成交额、换手率等）. It is categorised as a Read tool in the Sfc Data MCP Server, which means it retrieves data without modifying state.
Register the Sfc Data MCP server in PolicyLayer and add a rule for get_realtime_quote: 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 Sfc Data. Nothing to install.
get_realtime_quote 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_realtime_quote 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_realtime_quote. 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_realtime_quote is provided by the Sfc Data MCP server (yangxinagfeng123/sfc-data-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 →