AI agents call qlib_expression_help to retrieve information from Qlib without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool provides syntax documentation and help text for Qlib expressions—it is purely informational and performs a read operation with no side effects. It neither executes code, modifies data, deletes data, nor involves financial transactions. The blast radius of misuse is minimal since it only returns reference documentation.
From the tool's definition Tool name 'qlib_expression_help' and description '获取 Qlib 表达式语法帮助，包括常用算子和示例' (Get Qlib expression syntax help, including common operators and examples) indicate this retrieves documentation and help information.
Attacks that exploit this kind of access
获取 Qlib 表达式语法帮助，包括常用算子��示例。. It is categorised as a Read tool in the Qlib MCP Server, which means it retrieves data without modifying state.
Register the Qlib MCP server in PolicyLayer and add a rule for qlib_expression_help: 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 Qlib. Nothing to install.
qlib_expression_help 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 qlib_expression_help 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 qlib_expression_help. 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.
qlib_expression_help is provided by the Qlib MCP server (lsj210001/qlib-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 →