[HN Gopher] Machine Payments Protocol (MPP)
___________________________________________________________________
Machine Payments Protocol (MPP)
Author : bpierre
Score : 131 points
Date : 2026-03-18 15:24 UTC (7 hours ago)
(HTM) web link (stripe.com)
(TXT) w3m dump (stripe.com)
| NoahZuniga wrote:
| Didn't stripe already have a payments protocol?
| LoganDark wrote:
| MPP's supposed to eventually work with more than Stripe.
| david_shi wrote:
| It seems like this is designed for atomic purchases, could it be
| extended for subscriptions?
| jacobn wrote:
| > MPP provides a specification for agents and services to
| coordinate payments programmatically, enabling
| microtransactions, *recurring payments*, and more.
| david_shi wrote:
| https://docs.stripe.com/payments/machine/mpp
|
| Yeah I read that copy too, did you read the spec?
| dabbz wrote:
| I believe the Shared Payment Token is interchangeable with
| a payment method id that you attach to a customer object,
| but that link has very sparse information about how things
| actually work end to end and what objects mean what.
| lihorne wrote:
| Hey, I'm one of the developers at Tempo. We're working on an
| extension type for subscriptions to propose being added to the
| spec as well! We're starting with the simple types, but
| subscriptions are a natural extension. The subscription intent
| will work similarly to a one-time charge--the server returns a
| 402 with intent="subscription", and the client signs a
| recurring authorization.
| david_shi wrote:
| Cool, would be nice to get specifics on how payments are
| processed, failures, and cancellations re: the recurring
| model.
| codeulike wrote:
| _You 're absolutely right! I should have sent $5.00 for that
| transaction and not $500,000. I will generate a letter for you to
| print and sign and send to your bank to notify them of my
| mistake. Would you like me to generate a bankruptcy filing for
| you as well?_
| ezekg wrote:
| LLMs rarely admit fault, you gotta shift blame onto the user:
|
| > You're absolutely right! The transaction was submitted as
| $500,000 instead of $5.00. Since that's what was entered on
| your end, you'll need to contact your bank to resolve it. I
| will generate a letter for you to print, sign, and send to your
| bank if needed. Would you like me to generate a bankruptcy
| filing for you as well?
| leptons wrote:
| Claude always says it is sorry for screwing up when I point
| out that it screwed up.
| fragmede wrote:
| "Never apologize" into the customized instructions seems to
| work well for that specific issue.
| leptons wrote:
| This is the funniest (but seriously not funny at all) thing
| I've seen on the internet since the start of the whole "AI"
| craze. And it's all too true.
| simonmales wrote:
| I guess competition with the Bitcoin equivalent
| https://www.l402.org/
| jacobn wrote:
| And https://www.x402.org/
| danlitt wrote:
| What does this actually have to do with agents? What does the
| protocol include that makes this useful with AI rather than just
| a boring old program?
| uxhacker wrote:
| And would it not be useful to have some kind of human in the
| middle? For example what is to stop charge backs if no human
| has actually authorized the transaction?
| XzAeRosho wrote:
| There's a slightly new topic called Agentic Commerce, where you
| say for example: "purchase for me the most energy efficient
| dishwasher with a budget of $600", and the agent will connect
| via specialized via special MCP Servers and APIs to available
| stores, and will do the full purchase process for you.
|
| This MPP helps bridge the gap between the agent putting the
| product "in the basket", to actually completing the full
| purchase process.
|
| Disclaimer: I'm not in any way advocating for this use case,
| but it's part of my job to understand how it works. Part of
| what I do is try to help Agents understand, for example, what
| is "an efficient dishwasher" using actual data, and not
| hallucinated info.
| seanmcau wrote:
| I'm probably overlooking something, but what makes the
| problem of being able to get from item in basket to item is
| shipping different from choosing which item(s) to put in the
| basket?
|
| In other words, if Agents are able to navigate marketplaces,
| shouldn't that imply they can also navigate a subset of the
| marketplace, the payment section? Especially given that that
| section is "easier: theres no need for qualitative (or
| quantitative) judgement like there is for the shopping
| portion.
|
| Perhaps its a matter of proper safeguards?
| XzAeRosho wrote:
| It's not actually doing browser actions like Playwright or
| other browser automation tools, rather than direct API and
| MCP calls/actions. This is a whole new subset of API and
| connections that are all contained within the Agent
| context, no browser mocking. That's why they are creating
| these new protocols, so the full governance can work within
| the context of the Agent and its available tools.
|
| As I said, it doesn't have to make sense, but this is being
| pushed on us anyway...
| pythonaut_16 wrote:
| Thanks for sharing your insights!
|
| It seems like this workflow suffers the same problem as
| Alexa and Amazon dash buttons: consumers don't typically
| want the computer to just go buy things for them with no
| oversight. At least I don't.
|
| Adding a checkout step would make this more plausible to
| me. "Agent, go find the most efficient dishwasher under
| $600" where it adds its recommendation to a cart, or even
| "Find me the best dishwashers under $600" where it
| creates a catalog page with its recommendations and an
| easy checkout process with whatever store is actually
| providing.
| twalla wrote:
| As much as I detest having to look at ads or being
| "influenced" in any way, shape or form, I think the
| opportunities for exploitation with what you just described
| is potentially orders of magnitude more harmful. Sure, let me
| just hand my wallet to a stochastic black box with god-knows-
| what RL'd biases and then hook it up to adversarial data
| sources all vying to extract the most money from me - what
| could possibly go wrong?
| whalesalad wrote:
| This still does not answer the question. What makes this
| different from any other API request to Stripe?
| ezfe wrote:
| That's why it's called Machine Payments Protocol, instead of
| Agent Payments Protocol
| naomi_kynes wrote:
| MPP handles 'how do agents pay', but not 'did anyone authorize
| this'. For low-value API calls that's fine. But once agents start
| chaining transactions, you need a channel where the agent can ask
| a human 'I'm about to spend $2k on this, still in scope?' before
| the payment happens - not a fraud alert after. The authorization
| layer is a separate infrastructure problem from the payment
| protocol.
| rvz wrote:
| This is a good standard that I can get behind [0] since it's a
| serious proposal and submitted to the IETF [1] for MPP for
| machine-to-machine payments.
|
| A well thought out proposal for the long term, unlike MCP which
| is a complete joke of a "standard" and broken by design.
|
| [0] https://paymentauth.org/
|
| [1] https://datatracker.ietf.org/doc/draft-ryan-httpauth-
| payment...
| dbalatero wrote:
| Curious since I haven't followed super closely: what's busted
| about MCP?
| btown wrote:
| Jokes about wallet-draining aside, we're already giving our
| agents a real cash budget that they use for tokens. Our harnesses
| have mechanisms to manage that spend. And having an easily
| detectable protocol would allow the harness to ensure that its
| deterministic code is in play to make these payments - you'd give
| your payment details to the harness, not to the agent itself.
|
| And as to use cases, if I want quality outputs for automated
| research and discovery of a topic, in a world where quality
| journalism/scholarship _should_ be compensated and _does_ use
| tools like Cloudflare to block automated access, and where AI-
| generated content is _everywhere_ , it's optimal for me to want
| to spend some amount of the money I spend on tokens, on the
| ability for my agent to access reputable primary and secondary
| sources as needed.
|
| The challenge, of course, is that now there's an incentive for a
| spam source to try to get my agent to pay it, rather than the
| actual creator of the content. But there are interesting ways to
| solve this, because with these payment rails there's now an
| incentive for alliances of content creators to maintain indices
| of reputable sources and their canonical domains - perhaps even
| authoritative hashes of content. Lots of possibilities here.
| zer00eyz wrote:
| > we're already giving our agents a real cash budget that they
| use for tokens.
|
| I read this line and my (poor little) brain ran in a whole
| other direction for a moment. Because AI token management and
| "parental controls" aren't that far separated functionally.
|
| How far are we from the AI companies selling token packs like
| video games sell premium currency? Buy NOW, 1.99 for 10,000
| Anthropic gold...
| ccozan wrote:
| Last thing I heard: stock options are so last year, AI
| companies award ... tokens now. Can't find the source now,
| sorry!
| btown wrote:
| There was another comment I recall from today, discussing how
| OpenAI is not-so-subtly adopting a social-network-esque
| model, in how it's fine-tuned its chat system to always
| suggest another question that the user might want to ask.
|
| And the gacha gaming industry knows _exactly_ how to monetize
| this kind of trained instinct in a userbase. One might even
| call it a sense of pride and accomplishment...
|
| (But, to my larger point, if agentic harnesses can offer
| their LLMs a source of reputable input tokens from
| professional content providers, as an alternative to just
| more token back-and-forth with the model provider... that
| harness can at least direct some of that money towards
| producers of well-researched content.)
| vicchenai wrote:
| the real question for me is what happens when agents start
| hitting premium data APIs with MPP. right now if i want my agent
| to pull realtime financial data it has to go through my API keys
| with monthly billing. with MPP the agent could theoretically pay
| per-query directly to data vendors. thats a much better model for
| bursty workloads but the authorization problem naomi_kynes raised
| is real - you need spending caps that the agent cant override,
| not just logging.
| xmly wrote:
| Fascinating -- this is the future of decentralized finance.
| Agents will be the entities that both earn and consume.
| film42 wrote:
| Maybe. When it comes to actual payments, fee structures don't
| allow for this outside of the laboratory.
| 4k0hz wrote:
| "Decentralized" seems like a stretch for something developed
| and promoted by monolithic payment processors.
| gavinray wrote:
| I fail to see how "API call" is anything inherent to Agents/LLMs?
|
| Is this an attempt to get multiple payment processors to adopt
| the same Payments API so that agents fail less often?
| ezfe wrote:
| It has nothing to do with Agents/LLMs which is why it's not
| called "Agentic Payment Protocol."
|
| It's an API for making purchases instead of interacting with a
| website of unknown flow.
| gavinray wrote:
| The text literally starts with: > We believe
| agents will become an integral part of the internet economy,
| and they need the ability to transact with businesses and one
| another. > MPP provides a specification for agents and
| services to coordinate payments programmatically, enabling
| microtransactions, recurring payments, and more.
| ezfe wrote:
| Obviously agents are the big thing right now, but that
| doesn't change the fact that MPP is an automation solution
| neya wrote:
| I feel like the word "protocol", is just abused like it is a
| glorified marketing term. Kind of like how the word "hacker" was
| abused in everything else that had nothing to do with hacking.
|
| MCP was just a glorified way of tool calling but generated so
| much hype (and it eventually died down). Now we have MPP. Which
| again - could have just been another tool call exposed to the
| agent.
|
| Imagine you hire someone who claimed to have invented a new
| protocol and you're thinking of something like TCP or UDP, but
| all they share is just a markdown file.
| ai-inquisitor wrote:
| The good ol' folks at Stripe's collaborators Tempo Labs tried
| to make an RFC-style description page for MPP:
| https://paymentauth.org/ (full doc on IETF draft page:
| https://datatracker.ietf.org/doc/draft-ryan-httpauth-
| payment...)
|
| I almost was going to point it out as evidence there was
| thought put into it. Nope, it's flimsy and AI generated.
|
| Also, it contains provisions for scamming customers:
|
| > _403_ indicates the payment succeeded but access is denied by
| policy
|
| No, it doesn't explain how to refund payments for customers you
| deny access to.
| Xirdus wrote:
| This one is even worse IMO
|
| > Servers MAY return 402 when:
|
| > * Offering optional paid features or premium content
|
| This implies that a successful GET request to a resource that
| user already does have access to, might still return 402
| instead of 200. This makes 402 basically unworkable.
| pertsix wrote:
| An RFC is a request for comments, contributions.
|
| Are you open to contributing to this RFC?
| pear01 wrote:
| Was it AI generated? If so, should I just delegate my AI
| to do so?
| john_strinlai wrote:
| that doesnt sound nearly as fun as getting upvotes, if im
| honest
| darkwater wrote:
| Will they get a slice of the earnings in return by
| Stripe?
| brendan_j_ryan wrote:
| Hey! [0]
|
| Am the primary author of the core spec, alongside many others
| at Tempo and Stripe [0].
|
| As is customary with the IETF draft process, this is our
| first submission and we expect that we will continue to
| iterate with the broader community -- including yourself if
| you are interested in contributing [1]
|
| Thanks for feedback on those two points.
|
| Re: Refunds: This is a payment method specific implementation
| detail. e.g. this looks very different on cards vs. bank
| accounts vs. stablecoins. We will provide stronger guidance
| here to remove ambiguity in the spec
|
| Re: 403: This provision comes from the ability to have
| _multiple_ Authentication headers, which we view as a
| necessity for real-world utilization and also compatibility
| with the Authentication scheme. Similar to the above, we will
| provide stronger guidance for servers which may support a
| plurality of authentication schemes and need to handle this
| edge case.
|
| [0] Had to create a new account since it turns out many years
| ago I never set an email on my HN profile...
|
| [1] https://github.com/tempoxyz/mpp-specs
| NetOpWibby wrote:
| I recently redesigned my blog to look like a modern RFC and
| I'm loving the way they've decided to render tables in their
| plain text, definitely gonna steal that.
|
| On topic though, Stripe is trying to make themselves the
| Visa/Mastercard of crypto. They're in position to do so and
| it seems like Coinbase is their other half. I don't trust or
| like it though.
| ahnick wrote:
| The best Visa/Mastercard of crypto already exists and is
| called Flexa. (https://flexa.co/payments#pricing)
| NetOpWibby wrote:
| Oh wow, I never heard of this. I'm currently working on
| something similar with the same 1% rate, haha! WELP
| treyd wrote:
| I think this started when "web3" cryptocurrency projects
| started using the term to pretend that something which isn't
| much more than a service that uses a blockchain network to move
| money around was actually somehow "decentralized" and that that
| made it more trustworthy.
| devmor wrote:
| I've been thinking this, but never really put it into words.
|
| Every time I see one of these I think "You are just describing
| an API".
| sutib wrote:
| "they need the ability to transact with businesses and one
| another."
|
| Really, they _need_ it. How can we possibly live without
| computers spending money without supervision?
| user3939382 wrote:
| The more industrial activity and investment I see in "payments"
| and ecommerce, is to me a signal of a hollow society that has
| ceased creating real value. We have more to contribute than
| materialism, skimming off of electronic transactions,
| entertainment etc.
| quantium1628 wrote:
| the comments here are better than the article lol
| Animats wrote:
| "Creates a direct connection between your wallet and our bank
| account!"
|
| Note the absence of invoices, bills of lading, and receipts, all
| the things you need when a vendor doesn't deliver. All it does is
| send money, one-way. So it's useless in a B2B context.
| fhn wrote:
| All payments are final. Cancellations and refunds will be charged
| a 5% processing fee.
| glitchc wrote:
| It feels like an attempt to bypass PCI-DSS...
| giovannibonetti wrote:
| For those of you in Brazil, my company jota.ai has built a
| financial AI-assistant that you can chat with to open a bank
| account, connect with accounts from other banks, make instant Pix
| payments with any of them, all of that through WhatsApp right
| now. We're working hard to release long-running agents soon that
| can do increasingly complex workflows involving payments and
| whatnot.
|
| Please let us know if you have suggestions of what complex
| workflows you would like to build.
| ImPostingOnHN wrote:
| How do you keep customer information, credentials, and access
| secure from your employees (including yourself)?
| rickydroll wrote:
| As soon as you have a fungible currency, I expect that, from past
| experience, everyone who carries those packets will stick out a
| hand for a piece of the action. From a brief read of the
| description, I also expect attackers to work out a way to drain
| your account without you noticing.
|
| Regulation E limits your losses for electronic banking. Is this
| new payment system covered by Regulation E? What is the maximum
| loss a consumer would experience?
| Christhepurr86 wrote:
| old article but still relevant. some things don't change
| grigio wrote:
| There are more competing "payment protocols" than users
| davidliu847386 wrote:
| tldr for anyone skimming: the key insight is in section 3
| vishnuharidas wrote:
| Okay, I am NEVER letting an agent make payment autonomously. If
| there's a payment that has to be made, tell me, I will do that
| myself.
| benced wrote:
| This isn't incompatible with the agent placing the purchase. I
| already let Claude Code do _most_ of what it wants but make it
| ask permission before sending a message on Slack. An LLM having
| the capability to do X is not incompatible with it being
| deterministically forced to seek permission to do X.
| Seventeen18 wrote:
| Not everything must be a protocol. I believe we will see very
| interesting attacks vectors in the incoming years, especially
| when we see how unsafe are most of the agents harness.
___________________________________________________________________
(page generated 2026-03-18 23:00 UTC)