zendrop_call_ toolInvoke any Zendrop tool by name (passthrough escape hatch).
Find trending low-cost products, see which orders are still unfulfilled, check last month's revenue, estimate shipping to the US, or import a catalog product into your store.
PopMCPZendrop
The three tools below are always on. Once you connect, every tool Zendrop publishes for your account appears beside them, read live from Zendrop's own server.
3 tools in the full catalog: 2 read and 1 write. 3 load by default, and the rest are found with tool search.
zendrop_call_ toolInvoke any Zendrop tool by name (passthrough escape hatch).
zendrop_connection_ profileWhat this connection is and which Zendrop tools it can reach.
zendrop_list_ toolsList Zendrop's live tool set with parameter schemas.
Authorize once, then an endpoint your client signs into. Nothing to deploy, and nothing to install on the Zendrop side.
Click Authorize, sign in to Zendrop with the account that owns your store, and approve the access. There is no API key, store id or callback URL to set up. Connect your store inside Zendrop first so the product and order tools have data.
Fulfilling an order or importing a product runs as soon as the AI calls it. New connections are read-only, which hides every Zendrop tool that changes data and call_tool with it, and only clients ticked on the PopMCP consent screen reach Zendrop.
Drop the PopMCP URL into Claude, ChatGPT, Claude Code, Codex or any other supported client. It signs in through PopMCP with OAuth, so your Zendrop credential never leaves the server.
app.popmcp.com/mcpAsk for something harmless before the agent changes anything. Writes run as soon as it calls them, so confirm it reads the right account first.
What can my Zendrop connection do right now?
zendrop_connection_profileok
Then just ask for the work
“What can my Zendrop connection do right now?”
“Find trending products under $15 in the Zendrop catalog”
“Which of my Zendrop orders are still unfulfilled?”
“Estimate shipping to the US for this product before I import it”
One hosted endpoint, registered once per client. The same tools and the same permissions, whichever window the request comes from.
Add the PopMCP URL under Customize → Connectors and the tools appear in every chat.
The same endpoint, registered in the browser. Nothing to install on the machine you are working from.
Register PopMCP as a custom connector, then let ChatGPT read and update the account.
Wire the endpoint into Codex or the Codex CLI when a task needs live business context, not a fixture.
Register the remote MCP server in OpenCode's config for terminal-first and scripted agent runs.
Add PopMCP as an MCP server in Z.ai's desktop app and work the account from the same window.
FAQ
What teams ask before putting Zendrop behind an AI client.
No. Zendrop has no public REST API or API keys; its supported route for software is its own MCP server, protected by OAuth. PopMCP is registered with Zendrop, so you click Authorize, sign in to Zendrop, approve the access on Zendrop's consent screen and you are connected. Nothing is copied or pasted. Sign in with the account that owns the store, because the connection only sees what that account sees.
Exactly the ones Zendrop's MCP server publishes for your account. When you connect, PopMCP reads Zendrop's live tool list and turns each one into its own tool with Zendrop's parameters, covering the catalog, imported products, orders, order issues, stores, billing and reporting. list_tools re-reads the list, and call_tool runs any Zendrop tool by name, including one Zendrop added after you connected, so the coverage never lags behind Zendrop.
Only on a connection with writes allowed. PopMCP treats every Zendrop tool as a write unless Zendrop marks it read-only or its name starts with a read verb, and a read-only connection, the default, hides all of those plus call_tool. An owner or admin turns on writes for the connection when the AI should fulfil orders, import products or change store settings, and those then run as soon as the AI calls them.
Zendrop allows 120 read requests, 30 write requests and 10 fulfilment actions per minute. Everyday questions about products and orders stay well inside that, but a bulk job does not: importing a long product list or fulfilling a backlog of orders in one go can hit the write or fulfilment ceiling and get a 429 Too Many Requests. Ask the AI to work in smaller batches with a pause between them.
Usually because no store is connected on the Zendrop side, so there is nothing for the account's token to read. Sign in to Zendrop, connect your store, and ask again; there is no need to reconnect PopMCP. If every tool answers 401 Unauthorized instead, the access was revoked in Zendrop or a different Zendrop account was authorized, so disconnect and reconnect with the account that owns the store.
No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.
Any client that supports a remote Streamable HTTP MCP server: Claude Desktop, Claude Web, Claude Code, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.
Connect Zendrop in PopMCP first, then run claude mcp add --transport http popmcp https://app.popmcp.com/mcp in a terminal. Inside Claude Code, run /mcp and sign in to PopMCP in the browser window it opens, ticking Zendrop on the consent screen. The Zendrop tools are then available in that session, and no Zendrop credential is stored on your machine.
Yes. The Zendrop catalog is small enough that all 3 tool definitions load into every conversation, so your AI never has to search for one before it can call it.
A tool is something your AI calls, and there are 3 here. A trigger is an event PopMCP watches for on its own. Zendrop has no triggers yet, so everything on this page happens when your AI calls a tool.
Launch a hosted MCP endpoint for Zendrop, keep tool access under control, and start testing real workflow prompts right away.