AI agents call get_operation_data 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.
The tool appears to retrieve operational data (likely financial statement or performance metrics) from the A-share database. No description of modification, deletion, execution, or financial transactions. Consistent with other 'get_*' tools on the server which are data retrieval functions. The empty description is a limitation, but the name and context provide sufficient evidence for a Read classification.
From the tool's definition Tool name 'get_operation_data' and server context indicate data retrieval. Server purpose is to 'query Chinese A-share stock data' including financial reports.
Attacks that exploit this kind of access
get_operation_data. 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_operation_data: 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_operation_data 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_operation_data 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_operation_data. 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_operation_data 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 →