Check if a Lightning invoice has been paid and retrieve the spend token. Poll this after generate_invoice until the payment is confirmed.
AI agents call check_payment to retrieve information from Lightningprox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves payment status information with no side effects or state mutations. While it interacts with a financial system (Lightning payments), it does not move money, create charges, or commit financial obligations—it merely queries the result of a prior action (generate_invoice). It is therefore classified as Read rather than Financial.
From the tool's definition Tool performs a polling query to check payment status and retrieve a spend token. No data is created, modified, or deleted.
Attacks that exploit this kind of access
Check if a Lightning invoice has been paid and retrieve the spend token. Poll this after generate_invoice until the payment is confirmed. It is categorised as a Read tool in the Lightningprox MCP Server, which means it retrieves data without modifying state.
Register the Lightningprox MCP server in PolicyLayer and add a rule for check_payment: 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 Lightningprox. Nothing to install.
check_payment 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_payment 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_payment. 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_payment is provided by the Lightningprox MCP server (unixlamadev-spec/lightningprox-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 →