Agentspay

Explainer

Machine Payments Protocol (MPP): The Stripe and Tempo Standard for Agent Payments

As software starts paying software, machine payments protocols define how value moves without a human at the keyboard. The harder question is how to keep that spending governed.

Agent Payments Console

Pick an agent

Payment intent

intent:

Policy evaluation

Human approval required

This spend is over your approval threshold. Approve it to issue a scoped card, or deny it.

Scoped virtual card issued

Agentspay

single-use

Wallet budget

spent of

Audit trail

In short

A machine payments protocol is a standard that lets software, including AI agents, initiate and settle payments autonomously without a human completing each transaction. It defines how a machine proves authorization, presents a payment, and settles, often for small, high-frequency amounts like API calls or data access. Emerging examples sit at different layers, such as AP2 for authorization, ACP for checkout, and x402 for inline settlement. Because the payer is software, policy enforcement and an audit trail are essential to keep autonomous spend accountable.

What a machine payments protocol does

A machine payments protocol gives autonomous software a common way to authorize and complete a payment without a person in the loop for each transaction. It typically standardizes how a machine identifies itself, proves it was authorized to spend, presents or requests payment, and settles the amount. The goal is interoperability, so any compliant agent and any compliant counterparty can transact without a bespoke integration.

Why it is emerging now

AI agents increasingly act on a user or business behalf, buying APIs, data, compute, and services in real time. Card flows and manual checkout were built for humans and do not fit high-frequency, machine-speed spending. Machine payments protocols such as AP2, ACP, and x402 have appeared to give agents a native, interoperable way to pay across authorization, checkout, and settlement.

The governance gap

The same hole appears one layer up, in how MCP payments expose payment tools to agents. A protocol can move money between machines, but it does not decide whether a particular spend is wise, in budget, or authorized by the right person. Autonomous payers can loop, hallucinate, or be manipulated, so unconstrained machine payments are a real financial risk. This is the governance gap: standards handle the mechanics of paying, not the controls around it.

MPP: the standard Stripe and Tempo actually shipped

Since March 2026 the phrase has a specific referent as well as a generic one. The Machine Payments Protocol (MPP) is an open standard co-authored by Stripe and Tempo, developed openly and submitted to the IETF standards track, and it launched alongside the Tempo mainnet. It solves a problem that is slightly absurd once you see it: when an agent needs a paid API today, it meets an onboarding flow designed for a human, with an account to create, a pricing page to read and a subscription tier to pick. MPP replaces that with a three-step HTTP exchange. The server answers an unpaid request with HTTP 402 and a challenge stating what payment it accepts. The client returns a credential. The server returns a receipt along with the resource. Because it negotiates per request, an agent pays for exactly the calls it makes, with no contract, no seat and no minimum commitment.

What MPP has that x402 does not

Both standards revive HTTP 402 and both let software pay inline, so they get framed as rivals. The differences that matter in production are two. First, payment method surface: x402 is blockchain-only, while MPP treats the method as an extension point and ships production-ready support for stablecoins, cards and Lightning, with a permissionless path for anyone to add another. That single difference decides which one a company whose treasury will not touch crypto can adopt at all. Second, production primitives: idempotency, expiration, request-body binding and tampering mitigations are in the MPP base specification rather than being things you build around the protocol yourself. MPP also supports sessions, settling a run of requests as off-chain vouchers for sub-100ms latency and near-zero marginal cost before one on-chain settlement closes the batch.

The control MPP deliberately leaves out

Read the MPP specification looking for a spending limit and you will not find one. There is no budget, no cumulative cap, no counterparty allowlist, no velocity rule and no approval threshold, and no statement about who is responsible for setting them. That is a correct decision at the protocol layer, the same one ACP and AP2 made. It is still a gap at the program level, and MPP widens it more than the retail standards do for a structural reason worth stating plainly: sessions and per-request pricing exist precisely to remove friction. Friction is what used to make runaway agent spend visible. Once a payment costs a fraction of a cent and clears in under a second, the failure mode stops looking like one bad large purchase and starts looking like hundreds of thousands of tiny ones to an endpoint nobody vetted, discovered when the batch settles.

MPP now has a second major implementation to point at. Amazon added Machine Payment Protocol support to Bedrock AgentCore Payments when it went generally available on 18 August 2026, alongside x402. It carries the same division of labour: the protocol moves the money, and the one policy field is a per-session maximum amount in USD. Our AWS AgentCore spend controls page has the measured detail.

How Agentspay closes the gap

Agentspay is a rail-neutral control plane that adds governance on top of whatever machine payments protocol you use. It funds capped agent wallets, enforces spend limits and velocity rules, pauses transactions for human approval above a threshold, and records every payment in an immutable audit trail. The result is autonomous machine payments that finance and compliance can still sign off on, because money never moves without policy.

Whatever standard moves the money, Agentspay is the rail-neutral control plane that keeps it governed. See how it works and the control surfaces that enforce policy, approvals, and audit on every transaction.

Side by side

MPP compared with x402

The two HTTP 402 machine payment standards, and where they genuinely differ.

MPP x402
Authors Stripe and Tempo Introduced by Coinbase, now the x402 Foundation
Governance IETF standards track Linux Foundation, x402 Foundation since July 2026
Payment methods Stablecoins, cards, Lightning, custom Stablecoins only
Settles on Tempo, Solana Base and other public chains
Idempotency and expiry In the base specification Build it yourself
Request-body binding In the base specification Build it yourself
Off-chain sessions Yes, voucher settlement, sub-100ms No
Works without crypto Yes, via the card method No
Enforces a spend budget No No

Frequently asked

Questions people ask about Machine payments protocol

What is the Machine Payments Protocol?

MPP is an open standard for machine-to-machine payments, co-authored by Stripe and Tempo and submitted to the IETF standards track. A server answers an unpaid request with HTTP 402 and a challenge describing acceptable payment; the client returns a credential; the server returns a receipt with the resource. It is free to implement, with no licensing fee.

What is the difference between MPP and x402?

Both use HTTP 402 to signal a request needs paying. x402 is blockchain-only and settles in stablecoins. MPP treats the payment method as an extension point, shipping support for stablecoins, cards and Lightning, plus idempotency, expiration and request-body binding in the base specification. MPP sessions also settle off-chain vouchers for sub-100ms latency at near-zero per-request cost.

Does MPP work without cryptocurrency?

Yes. That is the main practical difference from x402. MPP ships production-ready card support, so the same HTTP 402 handshake can settle on a card rail for a buyer whose finance team will not hold stablecoins. It also supports Lightning and allows anyone to define a new payment method without an intermediary approving it.

Can machines pay each other without a human?

Yes, and it already happens. An agent can settle an API call, buy a dataset or pay another agent for a task with no person completing the transaction. What makes it safe is not the protocol but the policy around it: a funded wallet with a hard cap, a merchant allowlist, a velocity rule and a human approval gate above a threshold you choose.

What protocols do machine payments use?

Three standards cover different layers. AP2 handles authorization through signed mandates. The Agentic Commerce Protocol handles merchant checkout. x402 handles inline settlement over HTTP for micropayments. They are complementary, and a production stack commonly touches more than one.

How do you audit payments made by software?

Every transaction needs to be attributable to a named agent, its human owner, the intent that triggered it and the policy verdict that allowed it. That means writing an immutable record at decision time, not reconstructing it from a card statement later. Without that, month-end close turns into forensics across pooled charges nobody can explain.

Keep reading

More explainers

ServiceNow AI Control Tower

ServiceNow AI Control Tower

ServiceNow AI Control Tower is the most complete agent inventory and risk console a large US enterprise can buy, and it now reaches across AWS, Google Cloud and Azure. We read the schema ServiceNow ships to developers to answer the one question the rollout meeting always ends on: can it stop an agent from spending money? It cannot, and the reason is written into the data model.

Read

Gemini Enterprise

Gemini Enterprise

Google did something in August 2026 that the other agent platforms have not done: it shipped a hard monthly spend cap that genuinely stops usage instead of emailing you about it. That deserves credit, and it also moves the interesting question one step along. A cap that stops something is only as useful as the thing it is scoped to, so we went and measured what Google can actually point that cap at, in the API model Google publishes for anyone to read.

Read

Salesforce Agentforce

Salesforce Agentforce

Agentforce is the largest agent platform any US enterprise is likely to already own, and it moved to consumption billing, which means the meter now runs on what your agents do rather than on how many seats you bought. That raises a finance question the rollout deck rarely answers: when an Agentforce agent is loose in production, what actually stops it spending. We went and measured the answer in Salesforce own published object model rather than guessing at it.

Read

AWS AgentCore

AWS AgentCore

Amazon shipped the missing piece in August 2026. Bedrock AgentCore Payments went generally available, and it is a real payments product: an agent can now hold a wallet, meet an HTTP 402, pay, and carry on reasoning without a human in the loop. So the question a platform lead has to answer stopped being whether AWS gives agents money and became a narrower, more awkward one: how much of a spend policy did AWS actually ship? We went and measured it, property by property, in the API model AWS publishes.

Read

Microsoft Agent 365

Microsoft Agent 365

Microsoft shipped a control plane for AI agents, and it is a good one. It gives every agent an identity, a registry entry, an owner, a sponsor and a Conditional Access policy. Then somebody in finance asks the obvious follow-up question: fine, but what stops the agent from spending money? This page answers what Agent 365 costs, what it governs, and what we measured when we went looking for a dollar amount anywhere in Microsoft's agent governance surface.

Read

QuickBooks MCP Server

QuickBooks MCP server

Connecting an accounting system to an AI assistant is now a ten minute job. Deciding what that assistant is allowed to do once it is connected is the part nobody writes about, and it is the part your controller will ask about first. This page compares what the official QuickBooks, NetSuite and Xero MCP servers actually hand a model, measured rather than summarized from marketing pages.

Read

Payment MCP Servers

payment MCP servers

Every large payment company shipped an MCP server in the last eighteen months, and almost every write-up of them is a setup tutorial. The setup is the easy part. The question worth answering before you connect one to a production account is narrower and much less comfortable: what, exactly, can the model on the other end of that connection do to your money?

Read

PayPal Agentic Commerce

PayPal Agentic Commerce

PayPal made a bet that most merchants would rather not implement a commerce protocol at all. Where Stripe and OpenAI shipped a spec for you to build against, PayPal shipped two products that sit on top of the checkout you already have, and then bought a company to make the catalog half work. That choice is the whole story: it explains why Agent Ready needs almost no engineering from you, why there is nothing for an agent to discover about your store on the open web, and why the thing PayPal will not do for you is the thing that gets expensive later.

Read

Shopify Agentic Commerce

Shopify Agentic Commerce

Shopify switched agentic commerce on by default, so your store is probably already selling to AI assistants whether or not anyone on your team configured it. Instead of restating the announcement, we checked something you can check too: on September 2, 2026 we requested the machine-readable capability file that Shopify publishes for real storefronts, on fourteen well-known US brand domains, and read what it exposes to an agent. Eleven answered correctly. The three that did not share one trait, and it is quietly costing them agent traffic.

Read

Web Bot Auth

Web Bot Auth

Web Bot Auth is the reason your agent either gets served or gets throttled with the scrapers. Almost everything written about it repeats the same architecture diagram, so we did something different: on September 1, 2026 we fetched the published key directories of more than twenty major AI operators and infrastructure vendors to see who is genuinely signing their traffic. Four were. The results are in the first table.

Read

Tempo Blockchain

the Tempo blockchain

Tempo is the payments chain Stripe and Paradigm built, and it shipped with a protocol that lets software pay for things on its own. It settles machine payments in under a second. It has nothing at all to say about whether your agent should have paid.

Read

AI Agent Governance

AI agent governance

Every agentic AI governance framework published so far governs the same four things: identity, tools, data and prompts. Not one of them carries a budget. Here is what the real frameworks say, which guardrails actually bind at runtime, and what to do about the last mile none of them reach.

Read

A2A Protocol

A2A Protocol

Most explanations of the A2A protocol stop at the sentence that agents can now talk to each other. That was true in April 2025 and it is no longer the interesting part. A2A shipped version 1.0 in April 2026 under Linux Foundation governance, it runs in production inside Azure AI Foundry and Amazon Bedrock AgentCore, and the questions engineers actually get stuck on are narrower: what an Agent Card commits you to, when to reach for MCP instead, and what happens the first time one of your agents has to pay another one for the work. That last question has a specific answer, and it is not in the core spec.

Read

Mastercard Agent Pay

Mastercard Agent Pay

Nearly every article about Mastercard Agent Pay is a retelling of one press release from April 2025, the one where Mastercard said AI agents would be able to shop with Agentic Tokens and named Microsoft as the first platform. That was sixteen months ago, and four more things have shipped since. Reading only the launch coverage leaves you with roughly a quarter of the picture, and the missing three quarters are the parts that decide whether you can actually put this into production.

Read

Visa Intelligent Commerce

Visa Intelligent Commerce

Almost everything written about Visa Intelligent Commerce is a retelling of the April 2025 announcement, when Visa said AI agents would be able to pay with a Visa credential. Three more things have shipped since, including an open agent-identity protocol built with Cloudflare that most coverage does not mention at all. This page is the current version, checked against Visa’s own developer documentation and newsroom in August 2026.

Read

Stripe agentic commerce

Stripe agentic commerce

Most writing about Stripe and agentic commerce is still a retelling of the September 2025 launch week, when Stripe and OpenAI shipped Instant Checkout and published the Agentic Commerce Protocol together. Stripe has built a good deal more since then, and some of it points in a direction the launch coverage never anticipated. This page is the current version, checked against Stripe’s own documentation in August 2026.

Read

ChatGPT Instant Checkout

ChatGPT Instant Checkout

Almost every guide to ChatGPT Instant Checkout still reads like it was written the week it launched, walking merchants through how to apply and what the fee will be. OpenAI changed course in March 2026. Here is the accurate version: what Instant Checkout was, what the numbers actually looked like, what replaced it, and which parts of the stack are still very much alive.

Read

Google AP2

Google AP2

Most guides to Google AP2 still describe an Intent Mandate and a Cart Mandate, because most of them are rewrites of the September 2025 launch post. The specification moved. Here is what the Agent Payments Protocol actually defines today, and the one question it deliberately does not answer.

Read

Human in the loop AI

Human in the Loop AI

Every guide to human in the loop AI describes the same shape: the agent pauses, a person decides, the agent continues. The shape is right. What almost none of them ask is a harder question, which is where the pause is enforced, because a pause written into the agent's own code is a pause the agent is trusted to honor.

Read

AI agent cost

AI Agent Cost

Every cost guide for AI agents answers the same two questions: what does it cost to build, and what does it cost to run. Both are answerable, and both are on somebody's invoice. The third question is the one that ends up in a variance report, because the agent also spends your money, and nobody sends you a bill for that.

Read

Agentic checkout

Agentic Checkout

Nearly every guide to agentic checkout is written for the merchant who wants to receive these orders. Far fewer are written for the company whose agents are placing them, which is odd, because agentic checkout quietly removes the one screen where spending used to get a second look.

Read

API monetization

API Monetization

Most guides to API monetization argue about which pricing model wins. The harder question in 2026 is who is calling. An API priced for a signed-up developer with a key behaves very differently when the caller is an agent that showed up once, wants one record, and has no account.

Read

x402 protocol

x402 Protocol

x402 took the one HTTP status code the web never used and turned it into a payment rail machines can drive. The protocol is elegant and genuinely small. The part it deliberately leaves to you is the budget.

Read

AI procurement agents

AI Procurement Agents

Every major procurement suite shipped agents during 2026. Almost none of them answer the question your controller will ask first, which is what happens when the agent is wrong about a purchase and the money has already moved.

Read

Agentic payments

Agentic Payments

Agentic payments move money with no human at the checkout. The rails to do it all shipped during 2026. The part most teams have not solved is deciding, before the money moves, whether the agent was allowed to spend it.

Read

AI agent monetization

AI Agent Monetization

Every AI agent company is rewriting its price list. The models that survive are metered. The ones that quietly fail are the ones where nobody measured what a single task costs to serve.

Read

Agent payment platforms

AI Agent Payment Platforms

Five different kinds of product now call themselves an AI agent payment platform, and they solve five different problems. Picking the wrong category is the expensive mistake, not picking the wrong vendor inside a category.

Read

Universal Commerce Protocol

the Universal Commerce Protocol (UCP)

Google and Shopify shipped UCP as an open standard so an AI agent can check out at any merchant that supports it. Here is what the specification actually defines, where it is live for US buyers, and the one thing it deliberately leaves to you.

Read

MCP Payments

MCP Payments

MCP payments are how an AI agent discovers a payment tool and calls it to move money. The catch: the Model Context Protocol carries the tool call, not the spending decision, so nothing in the stack asks whether the purchase should have happened.

Read

Visa Intelligent Commerce vs Mastercard Agent Pay

Visa Intelligent Commerce vs Mastercard Agent Pay

Visa Intelligent Commerce and Mastercard Agent Pay are the two big card networks racing to let AI agents pay. They take different routes to the same idea, and neither one decides whether a given purchase should have happened.

Read

Agentic Commerce Protocol

the Agentic Commerce Protocol

ACP is the open standard behind agentic checkout in ChatGPT. It tells a merchant how to sell to an AI agent. It says nothing about whether your agent should have made the purchase.

Read

AP2 vs ACP vs x402

AP2 vs ACP vs x402

AP2, ACP, and x402 are the three standards shaping how AI agents pay. They solve different layers of the problem, and most real systems will touch more than one.

Read

Know Your Agent (KYA)

Know Your Agent

KYA, or Know Your Agent, extends the idea of customer due diligence to autonomous software. When an agent spends, you need to know which agent, on whose authority, and under what limits.

Read

Keep agent spending governed

Add policy, hard limits, human approval, and an immutable audit trail across any protocol or rail. Start in the sandbox today.

Never moves money without policy