机器支付协议 (Jīqì Zhīfù Xiéyì)
Machine Payments Protocol (MPP)

原始链接: https://stripe.com/blog/machine-payments-protocol

## 机器支付协议 (MPP) 摘要 人工智能正在迅速发展为自主代理,需要一种在线交易的方式。现有的金融系统是为人类设计的,对这些代理构成障碍——即使是简单的购买,也需要复杂的账户设置和手动流程。 为了解决这个问题,Stripe 和 Tempo 共同编写了机器支付协议 (MPP),这是一种开放标准,使代理能够进行程序化支付。MPP 通过共享支付令牌 (SPTs) 促进使用稳定币和传统支付方式的微交易和定期支付。 与 Stripe 集成的企业可以接受 MPP 支付,只需进行最少的代码更改,并且在 Stripe 生态系统内显示为标准交易(包括欺诈保护和支付)。Browserbase、PostalForm 和 Prospect Butcher Co. 等早期采用者已经利用 MPP 来进行代理驱动的商业模式。 MPP 简化了流程:代理请求资源,接收付款请求,授权付款,然后接收资源。Stripe 正在扩展其“Agentic Commerce Suite”以支持不断增长的代理经济,以及其他协议,如 x402 和 MCP 集成。

## 机器支付协议 (MPP) 摘要 Stripe 的机器支付协议 (MPP) 旨在促进代理(人工智能程序)与服务之间的直接、自动化支付。目前,代理依赖于人工控制的 API 密钥进行交易。MPP 提出了一种标准化协议,允许代理自主进行支付,为新的用例打开可能性,例如为访问内容向内容创作者付费,并实现“代理商务”——代理可以代表用户完成购买。 讨论强调需要强大的支出控制以防止滥用,例如预定义的预算以及内容创作者之间为验证可靠来源而建立的联盟。主要问题集中在授权上——确保支付符合用户意图——以及处理潜在的争议。 虽然有些人认为这与基于加密货币的解决方案相似,但 MPP 专注于与现有的支付系统(如 Stripe)集成。该协议正在向 IETF 提出作为机器对机器支付的标准,支持一次性交易和定期交易。它解决了代理*如何*支付的问题,但没有解决*是否*授权支付的问题,将授权层作为单独的挑战。
相关文章

原文

AI is evolving from question-and-answer chatbots to autonomous agents that can make comprehensive plans, execute actions, and evaluate outcomes. We believe agents will become an integral part of the internet economy, and they need the ability to transact with businesses and one another.

However, the tools of the current financial system were built for humans, so agents struggle to use them. Making a purchase today can require an agent to create an account, navigate a pricing page, choose between subscription tiers, enter payment details, and set up billing—steps that often require human intervention. 

To help eliminate these challenges, we’re launching the Machine Payments Protocol (MPP), an open standard, internet-native way for agents to pay—co-authored by Tempo and Stripe. MPP provides a specification for agents and services to coordinate payments programmatically, enabling microtransactions, recurring payments, and more.

Stripe users can accept payments over MPP in a few lines of code using our PaymentIntents API. Businesses can then accept payments directly from agents, in stablecoins as well as fiat with cards and buy now, pay later payment methods via Shared Payment Tokens (SPTs). 

MPP is already powering new agentic business models on Stripe. Browserbase, a browser infrastructure provider, now lets agents spin up headless browsers and pay per session. PostalForm helps agents pay to print and send physical mail. Prospect Butcher Co. lets agents order sandwiches for human pickup or delivery to anywhere in New York City. And agents can now programmatically contribute to Stripe Climate.  

“Parallel is built for a world where agents are the primary users of the web. We integrated machine payments with Stripe in just a few lines of code, and now agents can autonomously pay per API call for web access. This allows us to reach any agent developer in the world on the same Stripe stack we already run on,” said Parag Agrawal, founder of Parallel Web Systems.

How MPP works

An agent can request a resource from a service, API, Model Context Protocol (MCP), or any HTTP addressable endpoint, and the service responds with a payment request. The agent authorizes the payment, and the resource is delivered to the agent. 

For Stripe businesses, these payments appear in the Stripe API and Dashboard like any other transaction; the funds settle into a business’s existing balance, in their default currency, and on their standard payout schedule. The same Stripe infrastructure businesses rely on for human payments can work for agents, including tax calculation, fraud protection, reporting, accounting integrations, and refunds.

Building for the agent economy

Agents represent an entirely new category of users to build for—and increasingly, sell to. Stripe is building a broad set of agentic financial infrastructure to enable these important new patterns, via our Agentic Commerce Suite, Agentic Commerce Protocol (ACP), MCP integrations, and payment support for both MPP and x402. 

To get started with MPP using Stripe, read our docs and sign up for early access.

联系我们 contact @ memedata.com