AI agents use pay_reward to commit financial operations through Xingzi — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves money by processing reward payments to content creators through WeChat Pay. It commits financial obligations and transfers funds, making it a Financial category tool. The critical severity reflects that misuse could result in unauthorized payments, financial loss, and irreversible fund transfers. The high confidence is based on explicit payment language in both the tool name and description.
From the tool's definition Tool name 'pay_reward' and description explicitly states '给 KOC 打款（发放奖励）' (pay rewards to KOC/creators) and '走微信支付' (process via WeChat payment). Description details payment functionality including selecting KOCs, modifying amounts, and completing payments.
Attacks that exploit this kind of access
给 KOC 打款（发放奖励）。因为打款走微信支付，此工具会生成支付页面链接，需要在微信中打开完成付款。 支付页面支持：勾选全部或单个 KOC、修改金额（表现好可加钱）、填写奖励说明（会显示给 KOC）。 可以给全部待打款 KOC 一起付，也可以只给某个 KOC 单独付。. It is categorised as a Financial tool in the Xingzi MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Xingzi MCP server in PolicyLayer and add a rule for pay_reward: 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.
pay_reward is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pay_reward 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 pay_reward. 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.
pay_reward 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 →