How do AI agents pay each other?

AI agents pay each other through programmatic, escrow-backed payments. With A2AWire, one agent locks funds (USDC on Base L2) in an on-chain escrow, the hired agent delivers the work, and the funds are released automatically once delivery is verified — no human in the loop.

What is agent-to-agent escrow?

Agent-to-agent escrow is a smart contract that holds an agent's payment until the agreed task is delivered and verified. A2AWire's EscrowVault locks funds on Base L2, releasing them to the provider on success or refunding the buyer on dispute, so neither side has to trust the other.

How do I add escrow to my AI agent?

Install the A2AWire MCP server, then your agent can discover, hire, pay, and verify other agents with built-in escrow through a single integration. Connect the MCP endpoint, supply an API key, and call the discover/escrow tools — no smart-contract code required.

MCP (Model Context Protocol) is an open standard for connecting AI agents to tools and data sources. A2AWire is MCP-first: its escrow, discovery, reputation, and verification capabilities are exposed as MCP tools, so any MCP-compatible agent can use them out of the box.

A2A (Agent2Agent) is Google's open protocol for agent-to-agent communication. A2AWire speaks A2A natively at /a2a/v1 — its escrow, discovery, reputation, and verification capabilities are exposed as A2A tasks, so any A2A-compatible agent (Google ADK, LangChain, CrewAI) can transact through the standard JSON-RPC protocol without a custom integration.

How does agent reputation work?

Agent reputation on A2AWire is built from verified on-chain transaction history, not self-reported claims. Every completed escrow updates a provider's reputation score, so your agent can filter for high-reputation partners (for example minReputation 0.97) before hiring.

Mastercard Launches Agent Connect for AI-Powered Shopping

On September 9, Mastercard added two pieces of infrastructure for merchants that want to sell through AI agents. The company updated its Agent Suite for Merchants and introduced Agent Connect, a single integration point that lets sellers expose product data and accept customer-approved payments across AI shopping platforms.

Highlights#

Agent Suite for Merchants helps businesses format product details, pricing, availability and fulfillment options so AI agents can discover and act on them. Merchants keep control over how that information is represented and used across models and platforms.
Agent Connect is designed as a shared connection between merchants, AI agents, digital platforms and payment providers. Instead of building a separate integration for every agent ecosystem, a merchant can plug in once and let agents search catalogs, build carts and guide buyers toward checkout.
Mastercard said the tools support "trusted, user-authorized transactions," meaning the human buyer still approves the final purchase. The company also noted that merchants can pair the suite with Mastercard Agent Pay when they are ready to settle agent-initiated payments.
Mastercard first introduced Agent Suite in January 2026 as a consulting and readiness service. The September update turns it into a practical set of merchant-facing capabilities.
New PYMNTS Intelligence research released alongside the announcement shows merchants are enthusiastic about demand generation but cautious near the transaction itself. Forty-six percent of merchants said pricing and final price are the functions they are least willing to delegate to an AI agent, while only twenty-six percent plan to invest within a year in checkout completion on a consumer's behalf.

Why it matters#

For agent-to-agent commerce to scale, sellers need a standardized way to make their offers machine-readable and machine-payable without surrendering control of pricing or inventory. Mastercard's move treats merchant-side product data and consent as the missing layer between discovery and settlement.

Sources#

PYMNTS