获取所有持仓记录
AI agents call position_list to retrieve information from Stock MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns user's current stock positions without creating, modifying, or deleting any data. It has no side effects and falls squarely into the Read category. The severity is low as it only exposes financial data visibility, not the ability to execute trades or move funds. The confidence is high given the clear retrieval semantics despite the description being in Chinese.
From the tool's definition Tool name 'position_list' and description '获取所有持仓记录' (get all position records) indicate data retrieval without modification. The method retrieves existing stock position data.
Attacks that exploit this kind of access
获取所有持仓记录. It is categorised as a Read tool in the Stock MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Stock MCP Server MCP server in PolicyLayer and add a rule for position_list: 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 Server. Nothing to install.
position_list 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 position_list 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 position_list. 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.
position_list is provided by the Stock MCP Server MCP server (kinmeic/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 →