AI agents call get_invocation_code to retrieve information from X402hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool itself only retrieves and returns code snippets — it does not execute them or move money directly. It is a Read/fetch operation returning text. However, severity is elevated to medium because the returned code, if executed by an AI agent, would trigger financial payments via x402 pay-per-call APIs.
From the tool's definition Return copy-paste code (javascript/python/curl) that pays and calls a given x402 endpoint
Attacks that exploit this kind of access
Return copy-paste code (javascript/python/curl) that pays and calls a given x402 endpoint. It is categorised as a Read tool in the X402hub MCP Server, which means it retrieves data without modifying state.
Register the X402hub MCP server in PolicyLayer and add a rule for get_invocation_code: 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 X402hub. Nothing to install.
get_invocation_code 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 get_invocation_code 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 get_invocation_code. 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.
get_invocation_code is provided by the X402hub MCP server (zacharytroberts03-ctrl/x402hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_invocation_code is one line of X402hub'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 →