AI agents call search_cards to retrieve information from Ygocdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves card data from a Yu-Gi-Oh database based on search criteria. It has no capability to modify, delete, execute code, or perform financial operations. The search returns matching card records without side effects, making it a pure Read operation with low severity risk.
From the tool's definition Tool description states it searches cards by keyword (卡牌名称、效果文本等 - card names, effect text, etc.). The verb 'search' combined with 'get' operations on sibling tools indicates data retrieval only.
Attacks that exploit this kind of access
通过关键字搜索游戏王卡牌，可以搜索卡牌名称、效果文本等。. It is categorised as a Read tool in the Ygocdb MCP Server, which means it retrieves data without modifying state.
Register the Ygocdb MCP server in PolicyLayer and add a rule for search_cards: 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 Ygocdb. Nothing to install.
search_cards 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_cards 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_cards. 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_cards is provided by the Ygocdb MCP server (lieyanqzu/ygocdb-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 →