AI Agent Payments
Model Context Protocol for autonomous payments
Enable AI agents to make and receive payments autonomously using the Model Context Protocol (MCP). Built for the agentic economy.
Benefits
Autonomous Transactions
AI agents can pay for resources, APIs, and services without human intervention.
Budget Controls
Set spending limits, approved merchants, and transaction rules for your agents.
Audit Trail
Every agent transaction is logged with context about why the payment was made.
Multi-Agent Support
Manage payments across fleets of agents with hierarchical permissions.
Technical Details
MCP Integration
The @t402/mcp package provides MCP tools for payment operations. Agents can check balances, make payments, and verify transactions.
Tool Definitions
Standard MCP tools: t402_pay, t402_balance, t402_verify, t402_history. Compatible with Claude, GPT, and other MCP-enabled models.
Spending Policies
Define rules in JSON: max per-transaction, daily limits, approved recipients, required confirmations for large amounts.
Wallet Abstraction
Agents operate with derived keys or smart contract wallets. Parent accounts maintain ultimate control.
Code Example
import { createMCPServer } from "@t402/mcp";
const server = createMCPServer({
wallet: agentWallet,
policies: {
maxPerTransaction: "10.00",
dailyLimit: "100.00",
approvedRecipients: ["0x...", "0x..."],
},
});
// Agent can now use t402_pay tool
// Claude: "Pay $5 USDC to the API provider"
// → t402_pay({ to: "0x...", amount: "5.00", token: "USDC" })Use Cases
- 1AI agents paying for API access
- 2Automated content purchasing
- 3Agent-to-agent service payments
- 4Research agents buying data access
Supported Chains
Quick Links
Ready to implement?
Get started with our quickstart guide and have ai agent payments working in minutes.
Get Started