AI agents call get_theme_detail to retrieve information from Sfc Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves theme metadata and constituent stock information from the SFC financial data API. It performs a query operation with no side effects—it neither modifies data, executes code, deletes records, nor commits financial transactions. The blast radius if misused is minimal, as an AI agent could only retrieve publicly available financial theme information.
From the tool's definition Tool name 'get_theme_detail' and description '获取主题详情（主题介绍、成分股等）' (get theme details including theme introduction, constituent stocks, etc.) indicates data retrieval only.
Attacks that exploit this kind of access
获取主题详情（主题介绍、成分股等）. It is categorised as a Read tool in the Sfc Data MCP Server, which means it retrieves data without modifying state.
Register the Sfc Data MCP server in PolicyLayer and add a rule for get_theme_detail: 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 Sfc Data. Nothing to install.
get_theme_detail 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_theme_detail 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_theme_detail. 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_theme_detail is provided by the Sfc Data MCP server (yangxinagfeng123/sfc-data-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 →