AI agents call check_balance to retrieve information from Lpxpoly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/queries financial account balance information. Although it relates to a financial system (Lightning wallet), it does not itself move money, commit financial obligations, or execute transactions—it is purely informational and has no side effects. The severity is low because balance checks pose minimal risk; an AI cannot cause harm by reading its own balance.
From the tool's definition check_balance retrieves the current Lightning wallet balance in sats without modifying any data or state. The description states 'Check your LightningProx balance' which is a query operation.
Attacks that exploit this kind of access
Check your LightningProx balance in sats. Required to pay for LPXPoly analyses. It is categorised as a Read tool in the Lpxpoly MCP Server, which means it retrieves data without modifying state.
Register the Lpxpoly MCP server in PolicyLayer and add a rule for check_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 Lpxpoly. Nothing to install.
check_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_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_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_balance is provided by the Lpxpoly MCP server (unixlamadev-spec/lpxpoly-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 →