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.