AI agents call list_unpaid_awards to retrieve information from Xingzi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays a list of unpaid awards/rewards. It performs pure data retrieval with no side effects—it does not process payments (that is the responsibility of 'pay_reward'), delete records, or execute external operations. The description explicitly characterizes it as a viewing operation ('查看' = view/check).
From the tool's definition Tool name 'list_unpaid_awards' and description '查看待打款列表（已通过审核但还未付款的）' [View list of pending payouts (passed audit but not yet paid)] indicate a read-only query operation that retrieves financial data without modifying or executing payments.
Attacks that exploit this kind of access
查看待打款列表（已通过审核但还未付款的）. It is categorised as a Read tool in the Xingzi MCP Server, which means it retrieves data without modifying state.
Register the Xingzi MCP server in PolicyLayer and add a rule for list_unpaid_awards: 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 Xingzi. Nothing to install.
list_unpaid_awards 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 list_unpaid_awards 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 list_unpaid_awards. 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.
list_unpaid_awards is provided by the Xingzi MCP server (yylwdyx-commits/xingzi-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 →