Decode an bolt11 invoice, the output amount is in milisatoshis
AI agents call decode-invoice to retrieve information from Phoenixd MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that decodes and displays the contents of an existing invoice (amount in millisatoshis, presumably also payee/recipient and other metadata). It does not create, send, pay, or modify invoices or wallet state. While it operates in a financial context, decoding/parsing is purely informational with no financial impact.
From the tool's definition Tool name 'decode-invoice' and description 'Decode an bolt11 invoice' indicate this retrieves and parses invoice data without modifying state or executing financial transactions. No creation, modification, or payment action occurs.
Attacks that exploit this kind of access
Decode an bolt11 invoice, the output amount is in milisatoshis. It is categorised as a Read tool in the Phoenixd MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Phoenixd MCP Server MCP server in PolicyLayer and add a rule for decode-invoice: 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 Phoenixd MCP Server. Nothing to install.
decode-invoice 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-invoice 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-invoice. 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-invoice is provided by the Phoenixd MCP Server MCP server (sharmaz/phoenixd-mcp-server). 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 →