AI agents call yeepay_yop_api_detail 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.
Based on naming convention and sibling tools that perform informational queries (overview, product_detail, link_detail), this tool most likely retrieves or queries API details without modifying state. The empty description reduces confidence, but the pattern across the server (overview, detail, guide tools) indicates read-only data retrieval operations.
From the tool's definition Tool name 'yeepay_yop_api_detail' suggests retrieval of API details/information. Server context shows tools for 'obtaining information' from YOP platform. Description is empty, limiting certainty.
Attacks that exploit this kind of access
yeepay_yop_api_detail. 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_api_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 Yop. Nothing to install.
yeepay_yop_api_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 yeepay_yop_api_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 yeepay_yop_api_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.
yeepay_yop_api_detail 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 →