agent-payment-x402

Automate secure per-task payments for AI agents via MCP and x402 protocol.

3|2|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/agentmatters/mullai-bot --skill agent-payment-x402
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-payment-x402
Source: https://github.com/agentmatters/mullai-bot/tree/main/src/Mullai.Skills/Skills/claude-code-everything/agent-payment-x402
Command: npx skills add https://github.com/agentmatters/mullai-bot --skill agent-payment-x402

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enable AI agents to make autonomous payments with built-in spending controls. Uses the x402 HTTP payment protocol and MCP tools so agents can pay for external services, APIs, or other agents without custodial risk.

Core Features & Use Cases

  • x402 protocol integration: handles payment negotiation, budget checks, and retries on 402 errors.
  • Spending controls: per-task budget, per-session budget, allowlisted recipients, and rate limits.
  • Non-custodial wallets: supports ERC-4337-style accounts with orchestrator-enforced spend policies.
  • MCP integration: exposes standard MCP tools to slot into agent harness setups.

Quick Start

Configure a per-task budget and allowlisted recipients in your orchestrator, then invoke the agentpay tool to begin a payment.

Frequently Asked Questions about agent-payment-x402

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enable autonomous payments for AI agents with built-in spend controls?

You can enable autonomous agent payments by implementing the x402 HTTP payment protocol with MCP tooling, which handles payment negotiation, budget checks, and retries on 402 errors while enforcing per-task and per-session spending policies.

What is the x402 payment protocol and how does it work for AI agents?

The x402 payment protocol is an HTTP-based standard that enables AI agents to autonomously negotiate and complete payments for APIs or services, automatically handling 402 Payment Required errors through retries and integrated budget validation.

Can I use non-custodial wallets with ERC-4337 accounts for autonomous agent payments?

Yes, autonomous agent payments support non-custodial wallets using ERC-4337-style accounts, where an orchestrator enforces spend policies and ensures agents never hand over direct custody of funds during transactions.

How do I set spending limits and allowlists for agents making API payments?

You can configure spending limits by defining per-task budgets, per-session budgets, and allowlisted recipients within your orchestrator, which the policy enforcement workflow checks before approving any agent payment.

Does MCP integration support adding payment tools to existing agent harness setups?

Yes, the MCP integration exposes standard MCP tools that slot directly into existing agent harness setups, allowing you to invoke the agentpay tool to initiate payments without restructuring your current architecture.

What are the limitations of using autonomous payment policies for AI agents?

Autonomous payment policies are limited by their configured constraints: agents cannot transact with non-allowlisted recipients, exceed per-task or per-session budgets, or bypass rate limits enforced by the orchestrator's policy workflow.