Agentspay

Explainer

Visa Intelligent Commerce vs Mastercard Agent Pay: Agentic Payments Networks Compared

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.

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

Visa Intelligent Commerce and Mastercard Agent Pay are the two major card networks programs for letting AI agents make payments. Both issue scoped, tokenized credentials an agent uses at checkout, and both added machine-to-machine payments in June 2026. Visa leads with a single integration across four agent protocols; Mastercard leads with agent-to-agent settlement across cards, bank accounts and stablecoins. Neither one decides whether an agent was allowed to spend.

What Visa Intelligent Commerce is

Visa Intelligent Commerce is Visa program for letting AI agents pay with a Visa credential inside an agent experience. First announced in April 2025, it expanded in June 2026 with Intelligent Commerce Connect, a single integration through the Visa Acceptance Platform that gives merchants, agent builders and payment enablers one place to plug in. It handles payment initiation, tokenization, spend controls and authentication. The design choice Visa is pushing hardest is breadth of interoperability: Intelligent Commerce Connect supports payments initiated through four agent protocols (the Trusted Agent Protocol, the Machine Payments Protocol, the Agentic Commerce Protocol and the Universal Commerce Protocol) and can route transactions across both Visa and non-Visa cards. Visa also plugged its network into ChatGPT in June 2026, so an agent can complete a purchase at any Visa-accepting merchant. The credential an agent receives is a Visa-tokenized, merchant-specific token with scoped permissions, so a token minted for a flight is only usable with that airline for that trip window. Visa has since added an agent-identity layer and developer tooling around it; our deep dive on what Visa Intelligent Commerce actually ships covers the Trusted Agent Protocol, Intelligent Commerce Connect and the VIC APIs in full.

What Mastercard Agent Pay is

Mastercard Agent Pay is Mastercard agentic payments program, announced in April 2025 and built on Mastercard Agentic Tokens. Those tokens extend the same tokenization that already powers contactless, secure card-on-file and Payment Passkeys, so the trust model is familiar to issuers. Citi and US Bank were the first issuing banks to support it, with the program expanding through 2026. In June 2026 Mastercard added Agent Pay for Machines, a service that lets AI agents and connected systems pay one another automatically across the network, with some payments as small as fractions of a cent. Mastercard leaned into ecosystem breadth on the settlement side: more than 30 partners signed on, including Stripe, Adyen, Coinbase, Cloudflare, OKX, Ripple, Polygon and Solana, and settlement is supported across cards, bank accounts and stablecoins. Where Visa is emphasizing one integration across many protocols, Mastercard is emphasizing many rails a machine payment can settle over. Mastercard also co-developed the Verifiable Intent standard with Google and donated it to the FIDO Alliance in April 2026, alongside Google's donation of the Agent Payments Protocol, so the same tokens are expected to travel with signed proof of what the buyer authorized.

Where the two programs actually differ

On the fundamentals they rhyme. Both are card-network programs, both replace raw card numbers with scoped agentic tokens, both launched their agentic effort in April 2025, and both shipped machine-to-machine capabilities on the same day in June 2026. The differences are in emphasis. Visa Intelligent Commerce is positioned as one integration that speaks four agent protocols and reaches any Visa-accepting merchant, which is attractive if your priority is checkout coverage across the open standards. Mastercard Agent Pay is positioned around agent-to-agent settlement and a wide set of partners and settlement rails including stablecoins, which is attractive if your priority is machines paying machines for API calls, data and compute at high frequency. Neither is a walled garden: both can touch non-native cards, and both intend to interoperate with the emerging protocol stack rather than replace it.

What both networks give you, and what neither does

Both programs solve the credential problem well. An agent no longer needs a real card number pasted into a config file; it gets a token scoped to a merchant, an amount or a window, which is a genuine security upgrade. What neither program solves is the buy-side decision. Visa and Mastercard tell a merchant how to accept an agent payment and how to tokenize it. They do not tell the company whose agents are doing the buying which agent may spend, up to what amount, with which counterparties, how often, and who has to approve above a threshold. That is not a gap in their design; it is out of scope by design, because those are your policies, not the network policies. The risk is that a protocol-compliant, correctly tokenized transaction can still be a purchase you never wanted, made by an agent that looped on a retry, misread a quantity, or was steered by prompt injection.

Agentic tokens versus a shared corporate card

The honest comparison is not Visa versus Mastercard; it is either agentic-token program versus what most teams do today, which is hand an agent a shared corporate card number. On that comparison both networks win decisively. A shared card gives every agent the full credit line, no per-agent attribution, and a card statement at month end that nobody can reconcile to a specific process. A scoped agentic token limits blast radius and keeps the real number out of the agent context. But a token scoped to a merchant is not the same as a budget. It caps what one credential can do at one seller; it does not cap what a fleet of agents can spend across many sellers, nor does it pause anything for a human when an agent tries to renew a contract or buy compute far outside its normal pattern. That is where a control plane comes in.

How Agentspay governs spend on either rail

Agentspay is the rail-neutral control plane that sits in front of whichever network moves the money. You do not pick Visa or Mastercard and inherit their governance; you keep one policy layer that works across both. Every agent gets its own funded wallet with hard limits instead of a slice of a shared card. Each intended purchase is checked against policy before a credential exists: per-transaction ceiling, budget over a window, merchant allowlist, velocity rules. Spend above your threshold pauses for a human approval instead of going through. The agent then receives a scoped virtual card or delegated credential valid for that one purchase, riding Visa or Mastercard rails underneath, and every decision lands in an immutable audit trail tied to the agent, its human owner, the intent and the policy that allowed it. Adopt the network program that fits your merchants and settlement needs, and keep one place that never moves money without policy. The same logic applies whether the buyer is a shopping agent or a procurement agent.

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

Visa Intelligent Commerce vs Mastercard Agent Pay

How the two card-network agentic programs compare, and where a buy-side control plane still fits.

Dimension Visa Intelligent Commerce Mastercard Agent Pay
First announced April 2025, Intelligent Commerce Connect added June 2026. April 2025, Agent Pay for Machines added June 2026.
Core credential Visa-tokenized, merchant-specific tokens with scoped permissions. Mastercard Agentic Tokens, built on existing tokenization.
Emphasis One integration across four agent protocols; any Visa-accepting merchant. Agent-to-agent settlement and a wide partner and rail set.
Settlement rails Card rails, can route Visa and non-Visa cards. Cards, bank accounts and stablecoins.
Machine-to-machine Supported via the Machine Payments Protocol. Agent Pay for Machines, payments down to fractions of a cent.
Buy-side spend limits Out of scope; token scope is not a fleet budget. Out of scope; token scope is not a fleet budget.
Human approval and audit Not provided by the network. Not provided by the network.

Frequently asked

Questions people ask about Visa Intelligent Commerce vs Mastercard Agent Pay

What is Visa Agent Pay?

There is no product called Visa Agent Pay. Agent Pay is Mastercard’s program; Visa’s equivalent is Visa Intelligent Commerce. People search the two names crossed because both launched in April 2025 and do the same job, issuing a scoped, tokenized credential an AI agent can spend. If you meant Visa, see Visa Intelligent Commerce above; if you meant Mastercard, see Mastercard Agent Pay.

What is the Visa Trusted Agent Protocol?

It is the agent-identity layer Visa introduced on October 14, 2025, co-developed with Cloudflare, which Mastercard Agent Pay has no direct equivalent of. It uses RFC 9421 HTTP Message Signatures so a merchant can verify that a request comes from a real agent acting for a real consumer. We cover it in full on our Visa Intelligent Commerce page.

What is Visa Intelligent Commerce?

Visa Intelligent Commerce is Visa program for letting AI agents pay with a Visa credential. Through Intelligent Commerce Connect, a single integration on the Visa Acceptance Platform, it handles payment initiation, tokenization, spend controls and authentication, supports four agent protocols, and lets an agent complete a purchase at any Visa-accepting merchant using a scoped, merchant-specific token.

What is Mastercard Agent Pay?

Mastercard Agent Pay is Mastercard agentic payments program, built on Mastercard Agentic Tokens that extend its existing tokenization. Citi and US Bank were the first issuing banks. In June 2026 it added Agent Pay for Machines, letting AI agents and connected systems pay one another automatically across cards, bank accounts and stablecoins, with some payments as small as fractions of a cent.

What is the difference between Visa Intelligent Commerce and Mastercard Agent Pay?

Both are card-network programs that give AI agents scoped, tokenized credentials, and both launched in April 2025 with machine-to-machine features added in June 2026. Visa emphasizes one integration across four agent protocols and reach across any Visa-accepting merchant. Mastercard emphasizes agent-to-agent settlement and a wide partner set that settles across cards, bank accounts and stablecoins.

Can AI agents pay with a credit card?

Yes. Both Visa Intelligent Commerce and Mastercard Agent Pay let an AI agent pay with a card by issuing a scoped, tokenized version of it rather than the real number. The token is limited to a merchant, amount or window, so it is safer than pasting a card into an agent config. It still does not enforce a per-agent budget or require human approval on its own.

Are agentic payments safe?

Agentic tokens make the credential safer, because a scoped token limits what a single payment can do if it leaks. They do not make the spending safe on their own. An agent can still complete a fully compliant, correctly tokenized purchase it should never have made. Safety at the business level comes from spend limits, merchant allowlists, velocity caps, human approval above a threshold and an audit trail.

Do Visa and Mastercard agent payments stop overspending?

No. Both networks scope a token to a merchant or a transaction, but that is not a fleet budget. Neither program decides which of your agents may spend, up to what total, or who signs off above a threshold, because those are buy-side policies. If your agents are the ones spending, you need a control plane that enforces policy and pauses for approval before any credential is issued.

What is Visa Intelligent Commerce Connect?

Intelligent Commerce Connect is the expansion Visa announced in June 2026, extending the original Intelligent Commerce program Visa launched in April 2025. The underlying model is unchanged: an agent is issued a payment credential tied to a verified consumer and constrained by the conditions that consumer set, with Visa handling agent verification at the network level.

Which banks support Mastercard Agent Pay?

Citi and US Bank were the first issuers to commit to Mastercard Agent Pay, which Mastercard announced in April 2025. Agent Pay works through Agentic Tokens, an extension of Mastercard’s existing MDES tokenization, so issuers can support it on rails they already run rather than through a separate program.

Is Mastercard Agent Pay related to Google AP2?

Yes, through Verifiable Intent. Mastercard co-developed that standard with Google and donated it to the FIDO Alliance on April 28, 2026, the same day Google donated the Agent Payments Protocol and published version 0.2. The practical effect is that Agent Pay and AP2 are converging on shared, FIDO-governed proof that a person authorized a specific agent purchase.

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

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

Machine payments protocol

Machine payments protocol

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.

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