AI agents call yeepay_yop_java_sdk_user_guide to retrieve information from Yop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries documentation and usage guides for the YOP Java SDK. It performs read-only operations - fetching and presenting information without creating, modifying, deleting, or executing any operations that would affect data or systems. The ability to fetch detailed link information is still within the Read category as it retrieves existing data.
From the tool's definition Tool description states: '获取易宝支付开放平台(YOP)的yop-java-sdk的使用说明' (retrieve YOP Java SDK usage documentation). The verb '获取' (retrieve/get) indicates data retrieval without modification.
Attacks that exploit this kind of access
通过此工具，获取易宝支付开放平台(YOP)的yop-java-sdk的使用说明，内容中包含链接时可以调用工具yeepay_yop_link_detail进一步获取其详细内容. It is categorised as a Read tool in the Yop MCP Server, which means it retrieves data without modifying state.
Register the Yop MCP server in PolicyLayer and add a rule for yeepay_yop_java_sdk_user_guide: 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 Yop. Nothing to install.
yeepay_yop_java_sdk_user_guide 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 yeepay_yop_java_sdk_user_guide 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 yeepay_yop_java_sdk_user_guide. 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.
yeepay_yop_java_sdk_user_guide is provided by the Yop MCP server (yop-platform/yop-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 →