AI agents call get_sz50_stocks to retrieve information from A Share without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a static list of stocks in the Shenzhen 50 index—a read operation with no side effects. It fits the 'Read' category as it queries and returns data without modifying, executing code, or committing financial transactions. The user cannot cause harm by misusing a stock list retrieval.
From the tool's definition Tool name 'get_sz50_stocks' indicates data retrieval of Shenzhen 50 stock listings. Server description confirms query-oriented functionality for retrieving 'stock basics' and 'historical prices' with no mention of modifications or deletions.
Attacks that exploit this kind of access
get_sz50_stocks. It is categorised as a Read tool in the A Share MCP Server, which means it retrieves data without modifying state.
Register the A Share MCP server in PolicyLayer and add a rule for get_sz50_stocks: 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 A Share. Nothing to install.
get_sz50_stocks 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_sz50_stocks 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_sz50_stocks. 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_sz50_stocks is provided by the A Share MCP server (kissjerryfan/mcp_server). 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 →