Connect Claude or ChatGPT to your account over the Model Context Protocol: one address, no key to copy, what you approve, and how to disconnect one.
MarketplaceHub speaks the Model Context Protocol (MCP), so an AI assistant can read your account directly instead of you copying answers into it. Ask Claude or ChatGPT how many units of a SKU are left, which marketplace connection is failing, or whether last night's price push finished, and it reads the answer from your own data.
It is the same data the API serves, through the same permissions and the same request allowance. Nothing new is exposed.
There is one address:
https://api.marketplacehub.com/mcp
Add it as a custom connector in your assistant — in Claude, Settings → Connectors → Add custom connector; in other clients, look for "MCP server" or "custom connector". Paste the address and the assistant does the rest.
You do not create an API credential for this. Unlike the API pages, the assistant registers itself and then sends you to a normal MarketplaceHub sign-in page. There is no secret to copy and nothing to paste back.
After you sign in, MarketplaceHub shows a consent screen listing exactly what the assistant asked for — for example Read products and listings. Read it. Approving is what creates the access; nothing happens before you do.
Twenty-six tools. Eighteen only read — your products and their listings (and which of them need work), marketplace categories and the attributes they need, which marketplaces are connected and how healthy each one is, which background jobs are waiting, running or failed and whether one finished, your orders, what a shipping label through Amazon would cost for one and what may be sent to its buyer, and your ads (switched off for now).
The ads tools are switched off for now: MarketplaceHub does not send advertising data to AI assistants, so an assistant is not shown them. To read your ads, use the API with an API key.
Eight can change things, and an assistant gets those only if you approved the matching write permission:
An assistant you approved for reading is never even offered them.
When an assistant does change something, the change waits for you on the API page under Approvals until someone approves it. You can switch this off for an assistant you trust. Until you save your own limits on the Guardrails tab, an assistant may move a price by at most 10% in one change.
If something else in your account owns price, stock or orders, a change made through an assistant is still applied — and the answer names the owner, so the assistant can tell you rather than assume. See the Data Flow page.
An assistant that never sees the answer to a change may send it again. Every write tool is protected against that: a repeat of the same call returns the first answer instead of doing the work twice, so a lost reply cannot confirm one shipment twice or apply the same price change again. You do not have to switch anything on.
Open API → Assistants. Every assistant you have approved is listed with what it was allowed to do and who approved it. Disconnect removes it.
It then has to ask for your approval again before it can read anything. A token it already holds keeps working until it expires, up to an hour — so if you think a token has leaked, contact support as well. To stop every assistant at once, use Pause under Approvals.
The list belongs to the account rather than to one person, so a colleague can disconnect an assistant you connected, and you can disconnect theirs. Removing the connector inside the assistant stops it from their end; disconnecting here stops it from ours.
Tell us what you were doing and what happened — the notification text or a product SKU helps us find it fast.