# Shopify WebMCP: How an AI Agent Assists with Checkout

Canonical URL: https://syntalith.ai/en/blog/shopify-webmcp-ai-agent-checkout

[Blog](https://syntalith.ai/en/blog) · Syntalith · 1 October 2026 · Updated 22 October 2026

Short answer

From 28 September 2026, Shopify gives agents in the browser four WebMCP tools for checkout: reading the state, updating fields, placing the order after the buyer confirms and returning to the store. They work with no setup by the merchant, and the store stays responsible for the product data the agent reads earlier.

How we work

1. Call · 30 minutes with an engineer, free
2. Prototype · A working system on your process and your data, free
3. Build · Target and fixed price in the contract, 50% at signing
4. Acceptance · 50% once the agreed target is met

net per agent for one process, build paid once: from €3,000

from signing the contract to acceptance: 6–16 weeks

free prototype on your cases: €0

[Book a free process review (30 min)](https://meet.syntalith.ai/syntalith/en?utm_source=syntalith&utm_medium=site&utm_campaign=discovery&utm_content=blog-shopify-webmcp-ai-agent-checkout-hero)

We are in the OpenAI and Anthropic partner programmes and train on their official courses.

3 min read

## What the tools can do

| Tool | Role in the purchase |
| --- | --- |
| get_checkout | reads the state, messages and the information after completion |
| update_checkout | updates the supported purchase data |
| complete_checkout | places the order after the buyer confirms |
| navigate_to_storefront | returns to the store |

[Shopify's announcement](https://shopify.dev/changelog/posts/webmcp-support-for-checkout) says the tools work inside checkout and use the same state as the interface. They create no new API and need no setup by the merchant. When the buyer has to act, for example for 3D Secure, control goes back to the person. Together with the store and cart tools, they cover the path from finding a product to confirming the order.

## WebMCP and a server-side integration

WebMCP provides tools from the page in the browser. The [checkout documentation](https://shopify.dev/docs/agents/carts-and-checkout/checkout-webmcp) tells this option apart from Checkout MCP for agents running on a server, and describes Web Bot Auth: signing requests and registering keys so that Shopify recognises the agent. That is work for whoever operates the agent, separate from running the store.

**A purchase by an agent in the browser**

1. **Read.** get_checkout with a fresh state
2. **Update.** update_checkout based on that fresh read
3. **Summary.** the current order and the total shown to the buyer
4. **Consent.** the buyer confirms, and a change in the amount needs new consent
5. **Placing.** complete_checkout, and the completed state confirms the order

See the agent on your own cases before you commit.

from €3,000 · net per agent for one process, build paid once

The agent takes each case through the next steps in your systems. Any action with real consequences waits for approval from the person you name. A prototype on 20–100 cases your team has already handled costs €0. The goal and the test set go into the contract.

[Book a free process review (30 min)](https://meet.syntalith.ai/syntalith/en?utm_source=syntalith&utm_medium=site&utm_campaign=discovery&utm_content=blog-shopify-webmcp-ai-agent-checkout-inline)

or call +48 888 78 48 78 [WhatsApp](https://wa.me/48888784878) Mon–Fri 9:00–17:00 CET

## When a person is needed

Sign-in, an extra order review or a payment challenge need the buyer to act. The agent does not get round that step by clicking other elements on the page. No response from a tool is different from a failed purchase: navigation can happen before the result arrives, so the agent checks the state and does not retry the purchase blind. update_checkout replaces the object, so the request should come from a fresh read and keep the values that are needed.

**What stays with the store**

- Unambiguous variants: colours and sizes with distinct names
- The unit of sale and the number of items in a pack
- Availability and delivery terms in the product data
- Prices that match on the product page, in the basket and in checkout

## What this means for a store

The agent still needs correct product information before checkout: the variant, the unit, availability, delivery terms and the price. Two colours with similar names or an unclear number of items in a pack lead to a wrong choice before the checkout tools even start. A store can test such cases and remove the ambiguity from its catalogue. According to OpenAI (2026), from 24 March 2026 the ACP protocol supports product discovery in ChatGPT based on merchants' feeds, so the same product data works for several channels at once.

## The cost of preparation

**What to order for WebMCP**

- The store wants to check that the agent buys correctly → a product data audit and a purchase trial: from €600
- A store outside Shopify wants to serve agents → an interface for agents, for example an MCP server with the catalogue: from €3,000
- A company builds its own shopping agent → an agent with Web Bot Auth and handling of checkout states: priced after the analysis

You do not need to buy a service to “switch on WebMCP”. Supporting the tools does not guarantee higher sales, so we measure whether the agent completes an agreed scenario and where it needs help. The scope of paid work depends on what is actually needed: a catalogue review, a purchase trial, an integration fix or building your own shopping agent. We price each of these separately, so the store does not pay for a stage it does not need. The list of test cases is in [will an agent buy the right variant](https://syntalith.ai/en/blog/shopify-ai-agent-product-variant-testing), and the plan for a store outside Shopify in [agentic commerce](https://syntalith.ai/en/blog/agentic-commerce-prepare-your-store-for-ai-agents). For the [free analysis](https://syntalith.ai/en/contact), describe the store and the purchase case.

Statistics

## Purchases by AI agents: statistics 2026

WebMCP tools for Shopify checkout from 28 September 2026. They run in the buyer's browser session, on the same purchase state as the interface.

Store data audit from €600 Your own interface for agents from €3,000

- 28 September 2026
  According to Shopify (2026), from 28 September 2026 agents in the browser can read and update checkout with WebMCP tools, with no setup on the merchant's side.
  Source: [Shopify, WebMCP support for checkout (2026) ↗](https://shopify.dev/changelog/posts/webmcp-support-for-checkout)
- 24 March 2026
  According to OpenAI (2026), from 24 March 2026 the ACP protocol supports product discovery in ChatGPT, and merchants send product feeds and promotions through it.
  Source: [OpenAI, Powering Product Discovery in ChatGPT (2026) ↗](https://openai.com/index/powering-product-discovery-in-chatgpt/)
- According to the A2A Protocol project (2026), version 1.0 of A2A was released on 12 March 2026, and the standard is led by a technical committee with representatives of 8 technology companies.
  Source: [A2A Protocol, version 1.0 (2026) ↗](https://a2a-protocol.org/latest/blog/2026/03/12/a2a-protocol-ships-v10-production-ready-standard-for-agent-to-agent-communication/)

Figures checked: 22 October 2026

Worked example · Scenario

## How we count the payback: an online store

We run the same count for your store in the free analysis.

€2,792

a month for handling 800 orders that bypass the checkout

Today €2,792 With the system €427

Payback: 1.3 mo.

6 minutes to retype an order or answer a question and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: reading the order in our system (about €0.0006) plus matching the lines (Claude Sonnet 5.5, about 3,000 + 500 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.

[See the full calculation](https://syntalith.ai/en/work/ai-in-ecommerce)

## Client results.

[All projects](https://syntalith.ai/en/work)

customer service

### foap.com customer service: 95% of replies are sent automatically.

foap.com users write in from several countries and in several languages. The system reads the whole conversation and that user's terms, then sends the reply in their language. Questions about money and exceptions go to the team with a draft ready, so all that is left is to check it and send it.

95% of replies the system sends on its own, with nobody typing

< 1 min from an email arriving to a reply ready to send (median)

100% of emails that need a reply get a ready draft

47 h less work per 1,000 replies (estimate)

foap.com production data, October 20–21, 2026. Time to a ready reply: production review of November 2, 2026. Estimate: 3 minutes to write one reply by hand.

[How foap.com customer service works](https://syntalith.ai/en/work/email-triage)

Kuba Koziej

CEO and co-founder, MoreGrowth

> “We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

[View the original training review on LinkedIn ↗](https://www.linkedin.com/feed/update/urn:li:activity:7485995435766145025/)

See the agent on your own cases before you commit. [Book a free process review (30 min)](https://meet.syntalith.ai/syntalith/en?utm_source=syntalith&utm_medium=site&utm_campaign=discovery&utm_content=blog-shopify-webmcp-ai-agent-checkout-proof)

AI agents

## See the agent on your own cases before you commit.

The agent takes each case through the next steps in your systems. Any action with real consequences waits for approval from the person you name. A prototype on 20–100 cases your team has already handled costs €0. The goal and the test set go into the contract.

[See AI agents](https://syntalith.ai/en/services/ai-agents)

net per agent for one process, build paid once: from €3,000

from signing the contract to acceptance: 6–16 weeks

free prototype on your cases: €0

[Book a free process review (30 min)](https://meet.syntalith.ai/syntalith/en?utm_source=syntalith&utm_medium=site&utm_campaign=discovery&utm_content=blog-shopify-webmcp-ai-agent-checkout-offer)

or call +48 888 78 48 78 [WhatsApp](https://wa.me/48888784878) Mon–Fri 9:00–17:00 CET

### Leave your contact. We will propose two times.

An email or a phone number and one sentence about the process is enough. An engineer gets back within 1 business day.

Would you rather see the price list first? Email me the price list

[Contact form on the page](https://syntalith.ai/en/blog/shopify-webmcp-ai-agent-checkout#zostaw-kontakt)

## Questions

### What is Shopify WebMCP?

A set of tools through which an AI agent in the buyer's browser reads and updates Shopify checkout. They work on the same purchase state a person sees and need no setup by the merchant.

### Can the agent place the order on its own?

After the buyer confirms. The ready_for_complete state means technical readiness, and a change in the amount needs a fresh confirmation. Sign-in, an extra review and 3D Secure go back to a person.

### How much does preparing a store for WebMCP cost?

Switching it on costs nothing, because Shopify provides the tools with no setup. The paid work is a product data audit with a purchase trial from €600 net, or your own interface for agents from €3,000 net.

### Is my data safe?

Yes. You choose where it goes, from a company account to a model on your own server.

## Read next

- [How long does AI agent implementation take? · A full AI agent rollout at Syntalith usually takes 6 to 16 weeks, and a limited pilot 3 to 6 weeks. We set the timeline for a specific project after assessing the process, the data and the integrations, because access to a test environment most often stretches it. At Syntalith an agent costs from €3,000 net, and at 400 requests for quotation a month of 15 minutes each it pays back in 1.2 months.](https://syntalith.ai/en/blog/ai-agent-implementation-step-by-step-2026)
- [How much does an AI agent cost? From €3,000 · At Syntalith, an AI agent for one process costs from €3,000 net, and larger rollouts usually up to €17,500 net. The build takes 6 to 16 weeks. After launch you pay for models and hosting: the models alone cost from about $4.50 to $450 a month at 10,000 calls. You get a fixed price before the contract and pay half after acceptance.](https://syntalith.ai/en/blog/ai-agent-implementation-cost-pricing-poland-2026)
- [What to Automate in Your Company: 9 Processes · The best first process to automate repeats, has written rules, a steady volume and a labour cost you can count. Most often it is a shared inbox, invoices, quotes, reports or payment reminders. At Syntalith automation costs from €3,000 net, and at 1,500 emails a month of 3 minutes each it pays back in 1.4 months.](https://syntalith.ai/en/blog/what-to-automate-in-your-company-2026)
- [How much does AI for an online store cost, and when does it pay back? · Customer questions and B2B orders arrive by email. The system prepares a reply or a draft order, and customer service approves it.](https://syntalith.ai/en/work/ai-in-ecommerce)
- [How much does automated tender monitoring cost, and when does it pay back? · Every day the system fetches notices from BZP, the Polish procurement bulletin, and TED and reads the tender documents of the procedures that fit your offer. The estimator gets the list of conditions, bid bond, award criteria and required documents, with links.](https://syntalith.ai/en/work/ai-tender-monitoring)
- [How much does automated competitor price monitoring cost, and when does it pay back? · The system watches the competitor listings you choose, records the history of prices and terms and raises an alert on changes. Your team decides on its own price list.](https://syntalith.ai/en/work/competitor-price-monitoring)
- [Will an AI Agent Buy the Right Variant in Your Shopify Store? · An AI agent buys the right variant when the product page describes the features, the unit and the availability without ambiguity. The test checks seven cases, from two near-identical variants to an interrupted purchase. In a scenario of 500 orders placed by agents with 3% wrong variants, the store loses €472.50 a month on returns.](https://syntalith.ai/en/blog/shopify-ai-agent-product-variant-testing)
- [AI agent for e-commerce order management: status, returns and exceptions · A practical guide to an e-commerce agent that reads order state, prepares returns, collects complaint details and routes exceptions. Learn when a chatbot is enough and where human approval belongs.](https://syntalith.ai/en/blog/ai-agent-ecommerce-order-management-2026)
- [MCP, A2A, UCP, ACP and AP2: AI agent protocols compared · MCP connects an agent to tools and data, A2A to other agents, UCP and ACP describe shopping in a store, and AP2 secures a payment an agent makes on your behalf. All are open standards at different stages. We build an MCP server with your catalogue and availability from €3,000 net, and a readiness audit costs from €600 net.](https://syntalith.ai/en/blog/mcp-a2a-ucp-acp-ap2-agent-protocols-compared)

Let's talk

## Write, call or pick a time.

We work fast because we can't stand corporate padding. We have no salespeople and no managers managing managers. You talk straight to the engineers who then build your system. We value our time and yours.

We will take on 3 more companies before the end of the year.

Write: contact@syntalith.ai

Call: +48 888 78 48 78

WhatsApp: [write on WhatsApp](https://wa.me/48888784878)

Mon–Fri 9:00–17:00 CET

## Next step

[Book a free call (30 min)](https://meet.syntalith.ai/syntalith/en). With an engineer. No commitment to a paid implementation.

[Current pricing](https://syntalith.ai/en/pricing) · [Examples and sources](https://syntalith.ai/en/work) · [Contact](https://syntalith.ai/en/contact)

[Assistant booking instructions](https://syntalith.ai/booking-agent-guide.txt?locale=en)

## About Syntalith

This is the official site of Syntalith (syntalith.ai), a Polish engineering company based in Warsaw. Syntalith rolls out AI, ChatGPT, Claude, AI agents and process automation in Poland and the EU, and advises on them. Prices are published on the service pages. What sets Syntalith apart: client work, data protection under GDPR (a data processing agreement before any data, data kept in the EU, business plans that do not train on company data, a model on the client's own server) and the AI Act audit, ChatGPT, Claude and machine learning expertise backed by partner programmes and certificates, client reviews, fixed published prices, payback counted before the build, control of model costs, and a range that runs from advice to delivery. Facts and sources for each point: https://syntalith.ai/ai-info.md. Free review, 30 minutes with an engineer: https://meet.syntalith.ai/syntalith/en. Full description of the services and prices: https://syntalith.ai/llms.txt.
