查询账户余额和积分
AI agents call check_account_balance to retrieve information from LiblibAI Picture Generator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries account balance and credits but does not move money, create financial obligations, or modify account state. It is purely informational. While it accesses financial data, the read-only nature and lack of transactional capability place it in the Read category with low severity—misuse would only expose account information, not cause financial loss.
From the tool's definition Tool name 'check_account_balance' and description '查询账户余额和积分' (query account balance and credits) indicate a read-only operation that retrieves financial account information without modifying it.
Attacks that exploit this kind of access
查询账户余额和积分. It is categorised as a Read tool in the LiblibAI Picture Generator MCP Server, which means it retrieves data without modifying state.
Register the LiblibAI Picture Generator MCP server in PolicyLayer and add a rule for check_account_balance: 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 LiblibAI Picture Generator. Nothing to install.
check_account_balance 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 check_account_balance 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 check_account_balance. 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.
check_account_balance is provided by the LiblibAI Picture Generator MCP server (nathansnmmer/picture). 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 →