Add your mate to a BigCommerce store

BigCommerce is a hosted platform, like Shopify — there is no self-hosted plugin, so AI Assistant reaches a BigCommerce storefront through the universal embed (Storefront → Script Manager, the store's own supported way to inject a script — no theme edit required) plus a native single-click app for a one-step install.

Before you start

• A BigCommerce store with admin access to Settings.
• A Store-level API account (Settings → API accounts) if you want the native app path or an MCP connector reading your own catalogue and orders.
• Your workspace open in the Console.

1. Add the embed via Script Manager

The tag to paste is the one your Console connection settings show, with your workspace's own address:

<script src="https://your-assistant.busymate.ai/embed/v1.js" data-assistant="your-assistant" data-label="Ask us" async></script>

1. In the BigCommerce control panel, open Storefront → Script Manager.
2. Create a script and paste the tag.
3. Set it to load on the storefront, footer placement. The floating widget now appears on every storefront page — nothing else to configure for that part. This same script can also be created through the Admin API's Content Scripts resource (POST /v3/content/scripts) if you are scripting the install.

There is no hosted BigCommerce demo store to open yet — a trial store cannot be launched to the public without a plan, so none is shown. The install above is the whole of it; the catalogue read and the order lookup work the same way on your own store once the loader is in place.

2. Or install the native app (single-click)

For a one-click install instead of a pasted script, a BigCommerce app (registered on the developer portal) can install the same loader via the Scripts API on install, and add a "Chat with your mate" widget through the Widgets API in Page Builder. This is the same OAuth single-click pattern every BigCommerce app uses — see Connect an MCP server for the credential shape once installed.

3. Teach it your catalogue

Connect an MCP server reading your store's own Admin API v3 (products, categories) and orders — see Connect an MCP server. A store-level API account (Products + Orders read scope is enough for grounded answers) is all it needs; nothing is hardcoded, every answer reflects your live stock and prices.

4. Recognize signed-in customers

BigCommerce's Customer Login API identifies who is shopping. Register your own storefront (or a small backend you control) as an identity provider — see Recognize signed-in customers for the exact fields (issuer, JWKS URL, the launch endpoint) — then define window.BusymateAI.getIdentity in your Script Manager script before the embed <script> tag (the embed captures it once at load) so a signed-in shopper is recognized without asking twice, and can ask "where's my order" and get a real answer scoped to their own account.

Manage from any MCP client

Everything above is also a tool call — script install, connector registration and knowledge sources can all be driven from your own MCP client instead of the Console UI.

Verify

1. Open your storefront in a private window: the floating widget appears on every page.
2. Ask about a product: the answer uses your live price and stock.
3. Sign in as a customer and ask where your latest order is: the answer is about that order, and a signed-out visitor is asked to sign in instead.

Next

• Connect an MCP server: the catalogue and order connector.
• Recognize signed-in customers: the identity-provider fields.