MCP server
Connect Claude or ChatGPT to your account over the Model Context Protocol. One address, no credential to mint, and ten tools: eight that read your account, and two that update price, stock and shipments.
MarketplaceHub speaks the Model Context Protocol, 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 account.
It is the same data the REST API serves, through the same permissions and the same request allowance. Nothing new is exposed.
Connect an assistant
There is one address:
https://api.marketplacehub.com/mcpAdd 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 mint a credential for this. Unlike the REST API, 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.
What you are asked to approve
After you sign in, MarketplaceHub shows you a consent screen listing exactly what the assistant has asked for — for example Read products and listings. Read it. Approving is what creates the assistant's access; nothing happens before you do.
Three things worth knowing:
- The assistant only gets the permissions it asked for, and it can never be granted more than your API offers. A request for anything else is refused.
- Access is per assistant. Connecting Claude does not connect anything else.
- One item on that list is not a permission over your data: Stay connected. It lets the assistant keep working without sending you back to a sign-in page every hour. It reads nothing extra, and disconnecting the assistant ends it along with everything else.
What an assistant can do
Ten tools. Eight only read. Two can change your data, and an assistant gets those only if you approved the matching write permission — the consent screen names them, and an assistant you approved for reading is never even offered them.
Publishing a new listing is still not possible over MCP, deliberately: it writes to a marketplace against a schema that has to be got exactly right, which is a poor first thing to hand an assistant. Refunds are excluded for the same kind of reason — money moves.
| Tool | What it answers | Permission |
|---|---|---|
marketplaces_list | Which marketplaces are connected, and the health of each — including which one needs reconnecting | MarketplacesRead |
products_list | Your catalogue, paged, with the marketplace listings each product has | InventoryRead |
products_get | One product by SKU, and where it is listed | InventoryRead |
product_types_search | Finds a marketplace category to list a product under | InventoryRead |
product_types_schema | The attributes a category accepts, with the required ones flagged | InventoryRead |
jobs_get | Whether a background job has finished, and whether it worked | InventoryRead |
orders_list | Your orders, filtered by status or by when they changed | OrdersRead |
orders_get | One order | OrdersRead |
inventory_price_quantity | Writes. Sets price and/or stock for SKUs you name, and pushes the change to the connected marketplaces | InventoryWrite |
orders_confirm | Writes. Confirms shipment of order items, with carrier and tracking | OrdersWrite |
Retries cannot double up
An assistant that never sees the answer to a write may send it again. Both write tools are keyed 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. The assistant does not have to do anything for this; it is on by default.
Customer details are not sent by default
The two order tools leave the buyer's name and address out unless the assistant explicitly asks for them. Most questions about an order do not need them, and an assistant's context is not somewhere personal data should arrive by accident. This matches the REST API, where the same data is behind IncludeCustomerData.
It counts against the same allowance
An assistant's calls draw on the request allowance your account already has, per endpoint — it does not get a second one for speaking MCP. Every call also appears in API → Request Log in the app, next to your REST traffic, so you can see what an assistant read and when.
Rate limits, error codes and idempotency work exactly as they do for REST. See Conventions.
Stopping an assistant
Go to API → Assistants. Every assistant you have approved is listed there, with what it was allowed to do and who approved it. Disconnect removes it.
Disconnecting takes effect the next time the assistant asks for access: it has to ask for your approval again before it can read anything. An access token it already holds keeps working until it expires, so if you think a token has leaked, contact support as well.
The list belongs to the account rather than to one person — a colleague can disconnect an assistant you connected, and you can disconnect theirs. Removing the connector in the assistant itself (in Claude, Settings → Connectors) stops it from their end; disconnecting here stops it from ours.
If it will not connect
- Nothing happens when you paste the address. Check your client supports remote MCP servers with OAuth. Desktop and browser assistants generally do; older command-line tools may not.
- You sign in but the assistant reports an error. The most common cause is the sign-in window being closed before the redirect completes. Try again and let it finish.
- A tool says a permission is missing. The assistant asked for less than the question needs. Reconnect it and approve the wider set on the consent screen.