AI agents call get_trade_dates to retrieve information from Ashare without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical trading calendar information (which dates were trading days) between two specified dates. It is purely a data retrieval operation with no side effects, reversible modifications, code execution, data deletion, or financial impact. The default start date of 2015-01-01 further confirms it queries historical reference data. Classification as Read is appropriate.
From the tool's definition Tool name 'get_trade_dates' and description 'Trading-calendar flags between two dates' indicate a query operation that retrieves calendar data without modifying, executing commands, or causing financial transactions.
Attacks that exploit this kind of access
Trading-calendar flags between two dates (default: from 2015-01-01). It is categorised as a Read tool in the Ashare MCP Server, which means it retrieves data without modifying state.
Register the Ashare MCP server in PolicyLayer and add a rule for get_trade_dates: 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 Ashare. Nothing to install.
get_trade_dates 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_trade_dates 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_trade_dates. 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_trade_dates is provided by the Ashare MCP server (maimai-hqw/ashare-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 →