AI agents call search_theme 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 searches and retrieves concept theme information based on keywords. It is a read-only operation with no side effects—it queries existing data without creating, modifying, deleting, executing code, or moving money. The context of a financial data API and the presence of sibling tools like 'get_balance_sheet' and 'get_flash_news' further confirms this is a data retrieval tool.
From the tool's definition Tool name 'search_theme' and description '搜索主题（按关键词搜索概念主题）' (Search theme by keyword to search concept themes) indicate a search/query operation that retrieves theme data without modifying any state.
Attacks that exploit this kind of access
搜索主题（按关键词搜索概念主题）. 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 search_theme: 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.
search_theme 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 search_theme 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 search_theme. 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.
search_theme 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 →