AI agents call decode_lightning_charge_utils to retrieve information from Zbd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool decodes/parses a Lightning charge QR code to reveal its properties. It is a read/inspection operation with no side effects — it does not create charges, move funds, or modify data. Despite being on a financial server, decoding a QR code itself carries no financial risk.
From the tool's definition Understand the inner properties of a Charge QR code
Attacks that exploit this kind of access
Understand the inner properties of a Charge QR code. It is categorised as a Read tool in the Zbd MCP Server, which means it retrieves data without modifying state.
Register the Zbd MCP server in PolicyLayer and add a rule for decode_lightning_charge_utils: 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 Zbd. Nothing to install.
decode_lightning_charge_utils 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 decode_lightning_charge_utils 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 decode_lightning_charge_utils. 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.
decode_lightning_charge_utils is provided by the Zbd MCP server (zebedeeio/zbd-payments-typescript-sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
decode_lightning_charge_utils is one line of Zbd's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →