AI agents call get_wallet 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 wallet/financial balance information but does not execute transactions, modify data, or move money. It is a read-only operation that retrieves the state of a financial account. While it accesses sensitive financial information, the action itself is passive and carries minimal risk if misused by an AI agent—viewing a balance cannot cause direct harm. Classified as Read with low severity.
From the tool's definition Tool name 'get_wallet' and description '查看钱包余额（总收益、可提现、已提现、冻结）' (View wallet balance: total earnings, withdrawable, withdrawn, frozen) — purely retrieves financial account balance data without modifying or moving funds.
Attacks that exploit this kind of access
查看钱包余额（总收益、可提现、已提现、冻结）. 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 get_wallet: 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.
get_wallet 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 get_wallet 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 get_wallet. 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.
get_wallet 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 →