# [The agentic commerce protocol landscape: ACP, UCP, and MCP](https://rebilder.com/learn/agentic-commerce-protocol)

> ACP, UCP, and MCP explained: what each agentic commerce protocol covers, who backs it, why specs churn quarterly, and how merchants can prepare.

- **Updated:** 2026-08-05
- **Author:** Rebilder
- **Published:** 2026-08-05

This guide answers one question: which agentic commerce protocol does your store need: ACP, UCP, both, or neither yet? The short answer: each protocol covers less than the headlines imply, the specs are still churning, and the highest-return work happens before you implement either.

This is the landscape in mid-2026. ACP from OpenAI and Stripe, live since September 2025; UCP from Google and Shopify, launched January 2026; and MCP underneath both as the data connectivity layer. The guide covers what each one does, what implementing one commits you to, and how to prepare no matter which protocol wins your category.

## What an agentic commerce protocol actually is

An agentic commerce protocol is a machine-readable contract between a store and a shopping agent. Instead of parsing a product page built for human eyes, the agent hits a defined endpoint and gets structured answers: what you sell, what it costs, whether it is in stock, and, where the rails exist, a way to start a checkout. The protocols emerging now split that work into three jobs: **discovery** (structured product data and feeds), **transaction** (checkout an agent can initiate), and **connectivity** (a standard way to query merchant data as tools).

Why this layer exists at all comes down to what agents receive without it. Our reference capture fetches the same product page two ways: the full theme HTML weighs 91,226 bytes, roughly 22,789 tokens, with the first machine-readable price buried at character offset 23,185. The same buying facts as structured markdown: 1,315 bytes, about 328 tokens, price on line 4. A protocol formalizes that second experience behind a stable, versioned interface, so an agent does not have to hope your markup is parseable.

> **Read this before the vendor pitch** Protocols are the transaction layer, not the visibility layer. An agent that cannot read your store never reaches your checkout endpoint. That ordering matters for where you invest first; the preparation sequence at the end of this guide is built around it.

## The landscape at a glance

Three names dominate the conversation, and they are not competitors in a simple sense: two are commerce protocols from rival camps, and one is the data layer both camps stand on:

| Protocol | Who is behind it | Status | What it covers |
| --- | --- | --- | --- |
| ACP (Agentic Commerce Protocol) | OpenAI + Stripe | Live since Sept 2025 | Product feed + agent-initiated checkout on real payment rails |
| UCP (Universal Commerce Protocol) | Google + Shopify; Etsy, Wayfair, Target, Walmart backing | Launched Jan 2026 | Catalog + checkout handoff |
| MCP (Model Context Protocol) | Broad ecosystem | Ongoing adoption | Data connectivity: merchant data (catalog, inventory) exposed as tools agents can query |

One more piece completes the picture: as of mid-2026, all three major card networks support agent-initiated payments. The payment layer, for years the obvious objection to “agents buying things”, has stopped being the blocker. What remains unsettled is everything above it: the specs themselves.

## ACP: the OpenAI and Stripe checkout rail

If a planning document near you says “the OpenAI Stripe agentic commerce protocol,” this is the one it means, usually shortened to the ACP protocol or just ACP. Live since September 2025, it was the first of the two commerce protocols to put agent-initiated checkout on real payment rails: a merchant exposes a product feed, and an agent can move from recommendation to purchase without a human re-typing card details. Stripe’s take on ACP transactions, roughly 4%, is the market anchor for what agent-originated checkout costs.

The most important thing to understand about ACP is a shift OpenAI made after launch: away from in-chat checkout, toward **discover in chat, transact on the merchant’s site**. The agent finds and shortlists; the human lands on your store to finish. Two consequences follow. First, implementing ACP’s checkout flow is not the whole story even inside OpenAI’s own ecosystem. Second, the merchant-side handoff (what your site does when an agent-referred buyer arrives) is now a live surface, and almost nobody generates it dynamically. The referred human who lands on your page converts ~38% higher than a search visitor; the page they land on is still yours to get right.

## UCP: the Universal Commerce Protocol

UCP launched in January 2026 from Google and Shopify, with Etsy, Wayfair, Target, and Walmart backing it: the other half of the market getting its protocol, four months after ACP. The backer list is the point: between them, these companies run the search surface and the storefront infrastructure a large part of retail already depends on.

In scope terms, UCP covers the catalog and the checkout handoff: the structured product data an agent reads, and the mechanism for passing a ready-to-complete purchase to the merchant. Discovery is designed to be self-serve: agents probe a well-known path (`/.well-known/ucp`) to learn whether a store speaks the protocol at all. When requests like that arrive, Rebilder’s Console logs them as kind `protocol` today, so you can watch demand for an endpoint you have not built yet.

## MCP: the data layer underneath both

MCP is not a commerce protocol in the checkout sense; it is the data connectivity layer the agent ecosystem has settled on: a standard way for an agent to discover and call tools that query structured sources. In commerce terms, that means a merchant can expose catalog and inventory lookups as tools, and any MCP-speaking agent can use them without custom integration work.

Because MCP is general-purpose, it slots underneath both camps rather than competing with either. A store that gets its product data into clean, queryable shape once can serve an ACP feed, a UCP catalog, and an MCP tool server from the same source of truth, which is exactly how Rebilder is built: a UCP catalog and checkout-handoff endpoint, an ACP product feed, and an MCP server exposing catalog and inventory tools, all reading the same wiring the gateway uses for markdown.

## Spec churn: the real cost of implementing early

Here is the operational reality the launch posts skip: these standards churn roughly quarterly. UCP, ACP, and the agent-verification specs around them are young, moving, and revised on a cadence that treats your integration as a fast follower. An endpoint you hand-build this quarter can drift out of conformance the next, and the failure mode is quiet: agents stop transacting, and nothing on your side throws an error.

This is why version discipline matters more than implementation speed. Our approach treats each spec release as immutable:

- **One directory per spec version** (for example `protocols/ucp/v0.x/`). An adapter targets exactly one published spec release, never “latest.”
- **Upgrades are additions, not edits.** A new spec version lands as a new directory with conformance tests green, plus a deprecation note on the old one, never an in-place rewrite.
- **Conformance tests against published suites**, run in CI, so drift is caught by machines instead of by lost orders.
- **Payments delegate to your PSP.** Payment execution stays with the merchant’s existing payment provider, because a gateway layer should never hold funds.

Whether you build in-house or buy, ask any vendor the same two questions: which exact spec versions do you pin, and what happens to my integration when the spec revs? “We track spec changes so you don’t” is the actual product being sold in this layer, so evaluate it as such.

## How to prepare without betting on a winner

You do not have to pick a camp to act. The numbers argue for moving on the layer beneath the protocols first, the one every agent already uses today:

- **~7x**: Cyber Week 2025 sales growth, agent-integrated vs. non-integrated retailers
- **~38%**: Conversion lift, AI-referred visitors vs search
- **~4.2x**: Content negotiation vs llms.txt, accurate retrieval

1. **Make your store legible to agents now.** Content negotiation, which answers `Accept: text/markdown` with clean structured text, is live technology, free to serve, and measured ~4.2x more effective than llms.txt alone for accurate retrieval. [Rebilder’s gateway](/docs/quickstart) does this today with adapters for Next.js, Shopify, Express, Fastify, and Cloudflare Workers.
2. **Publish llms.txt with the right expectations.** It is a useful index and the gateway [generates it](/docs/llms-txt) from your source data, but the same mid-2026 study found no citation lift from llms.txt alone. Ship it; don’t mistake it for the strategy.
3. **Watch for protocol probes.** The Console visit log [classifies every request](/docs/classification) as agent, human, crawler, or `protocol`, so hits on paths like `/.well-known/ucp` and `/mcp` are visible before you have built anything. That is real demand data for the build-or-wait decision.
4. **Consolidate your source of truth.** Price, availability, shipping, and returns in one structured place is the prerequisite every protocol shares. The wiring that feeds gateway markdown today is the same wiring an ACP feed, UCP catalog, or MCP tool server reads later; none of it is throwaway.
5. **Let the specs churn before you hand-roll.** Unless transacting agents are already a measurable share of your traffic, implementing a quarterly-moving spec by hand buys mostly maintenance. Rebilder ships version-pinned endpoints for all three, so the sequence above is the preparation they plug into.

> **What Rebilder ships today** The free gateway (agent detection, markdown via content negotiation, llms.txt generation, five adapters) and the Console (visit log, side-by-side preview, install). Protocol endpoints are live too: UCP catalog and checkout handoff, ACP product feed, and MCP catalog/inventory tools, each version-pinned with its own conformance suite, plus Web Bot Auth agent verification. Checkout is a redirect handoff onto your own PSP rails, so nothing here holds or moves funds.

## What is the agentic commerce protocol?

There is no single one. “Agentic commerce protocol” covers a small family of standards that let AI agents read stores and transact with them. The two named players are ACP (Agentic Commerce Protocol, from OpenAI and Stripe, live since September 2025) and UCP (Universal Commerce Protocol, from Google and Shopify, launched January 2026), with MCP serving as the general data connectivity layer underneath.

## What is the OpenAI Stripe agentic commerce protocol?

That is ACP, the Agentic Commerce Protocol, live since September 2025. It gives agents a product feed to read and a checkout they can initiate on Stripe’s payment rails, with Stripe’s roughly 4% take as the market anchor for costs. Note OpenAI’s post-launch shift: discovery happens in chat, but the transaction increasingly completes on the merchant’s own site.

## What is the UCP Universal Commerce Protocol?

UCP launched in January 2026 from Google and Shopify, with Etsy, Wayfair, Target, and Walmart backing it. It covers the catalog and the checkout handoff, and agents discover support by probing a well-known path (`/.well-known/ucp`) on your domain.

## What is the difference between ACP and UCP?

Camp and coverage. ACP comes from OpenAI and Stripe (live September 2025) and pairs a product feed with agent-initiated checkout on Stripe rails; UCP comes from Google and Shopify with major retailer backing (January 2026) and covers catalog plus checkout handoff. Neither replaces your store, both specs are still churning, and most merchants are better served preparing the shared data layer than picking a side early.

## Is MCP an agentic commerce protocol?

Not strictly. MCP is the general data connectivity layer agents use to query structured sources as tools, and commerce is one use of it. For a merchant, MCP support means exposing catalog and inventory lookups as tools any MCP-speaking agent can call. It complements ACP and UCP rather than competing with them.

## Do I need to implement ACP or UCP right now?

For most stores, not yet, because the specs churn roughly quarterly and an unmaintained endpoint fails silently. The higher-return move today is legibility: serve agents clean structured content via `Accept: text/markdown` (measured ~4.2x more effective than llms.txt alone for accurate retrieval), consolidate your product data, and watch your visit log for protocol probes. That preparation feeds any protocol endpoint you adopt later, including Rebilder’s own, which are live and version-pinned.

## Related

- [AI search optimization: the definitive guide](https://rebilder.com/learn/ai-search-optimization)
- [What is agentic commerce?](https://rebilder.com/learn/what-is-agentic-commerce)
- [AI shopping agents: what they are and how they read your store](https://rebilder.com/learn/ai-shopping-agents)
- [Gateway quickstart](https://rebilder.com/docs/quickstart)
- [How agent detection works](https://rebilder.com/docs/classification)
- [Free llms.txt generator](https://rebilder.com/tools/llms-txt-generator)