Get the previous trading day before the given date.
AI agents call previous_trading_day 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 historical calendar/trading date information. It queries existing data (trading day schedules) and returns a result without creating, modifying, deleting, or executing any operations. This is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'previous_trading_day' and description 'Get the previous trading day before the given date' indicates data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access previous_trading_day gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and A Share, and nothing reaches the server without passing your rules. This is the rule we recommend for previous_trading_day:
{
"version": "1",
"default": "deny",
"tools": {
"previous_trading_day": {}
}
}previous_trading_day is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the previous trading day before the given date. 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 previous_trading_day: 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.
previous_trading_day 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 previous_trading_day 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 previous_trading_day. 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.
previous_trading_day is provided by the A Share MCP server (shouldnotappearcalm/a-share-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from A Share, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
55 A Share tools catalogued and risk-classified — across an index of 43,000+ MCP servers.