A laptop showing Square payment, order, and customer screens, linked by a connector to a friendly AI assistant

Square MCP Server: What It Does and How to Connect Square to AI in 2026

Yes — Square has an official MCP server. The remote server at mcp.squareup.com lets any approved MCP-compatible AI tool sign in with your Square account and work against the full Square API: payments, orders, customers, catalog items, invoices, bookings, and more. It’s maintained by Square (Block) and is currently in beta. So if you’re searching “Square MCP,” the connection you want does exist.

The thing worth knowing before you set it up: an MCP server hands your Square account to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches Square for you, nothing fires when a payment comes in or an order ships, and nothing runs while the chat is closed. Here’s exactly what the Square MCP does, how to turn it on, where it stops — and what to use when you want Square work that runs on its own.


What the Square MCP server does

Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, Cursor, Goose, Windsurf, and others — talk to an outside app through a shared interface. Square maintains an official server, hosted remotely at mcp.squareup.com/sse, that exposes its whole API platform through a small set of MCP tools (the AI discovers the right service, checks the shape of the request, then makes the call).

With it connected, an AI client can:

  • Look up payments and orders — “show me today’s card payments over $200” answered from live Square data, not a guess.
  • Query customers and catalog — pull a customer’s purchase history, check stock on a catalog item, find a segment.
  • Create and update — draft an invoice, add a catalog item, update a customer record, or create a booking without opening the Square dashboard.
  • Reason across your account — summarize a day’s sales, spot refunds and disputes, or reconcile an order against a payment on the spot.

It reaches a wide surface — payments, refunds, checkout, disputes, customers, loyalty, catalog and inventory, invoices, payouts, bookings, and staff features are all in scope. It’s genuinely useful for ad-hoc work: ask a question, get an answer grounded in your real Square data, make a change without leaving the chat.

How to set up the Square MCP server

The remote server is the quick path — no code, no hosting, no access tokens to manage:

  1. In your AI client’s connector settings, add a remote MCP server pointing at https://mcp.squareup.com/sse.
  2. Sign in through the OAuth prompt with your Square account, authorizing only the scopes you want the AI to have. Square recommends the remote server precisely because it handles auth this way.
  3. Confirm the tools appear in the client, then start a chat and ask it to read a payment or update a record.

Two things to expect. First, Square keeps an allowlist of approved MCP clients to block malicious ones, so a less common client may need approval through Square’s developer forum before it can connect. Second, if you’d rather run it yourself, there’s a local option (the square/square-mcp-server project) that uses a manual access token against your sandbox or account — but for most people the hosted remote server is the one you want. Square’s MCP documentation covers both.

Where the Square MCP stops

None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:

  • It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch Square; it waits for you to ask.
  • No triggers. A new payment, a refund, an order marked fulfilled, a low-stock item, a booking canceled — none of these can start anything through MCP. There’s no “when this happens in Square, do that.”
  • It’s one app at a time. The Square MCP knows Square. Getting a paid order into QuickBooks, a Slack channel, and a Google Sheet means wiring up (and authing) a separate MCP server for each, then hoping your client can juggle them in one turn.
  • You own the plumbing and the scopes. OAuth scopes, client approval, and the blast radius of read/write access to your payments and customer data are all on you.

So the Square MCP is a great way to ask Square things and make one-off edits. It is not a way to make Square run — to have work happen on a schedule or in reaction to an event, across the other tools an order or payment touches.

Running Square work that doesn’t need a chat open

That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Square natively — no MCP server to host, no OAuth plumbing to maintain, no client allowlist to clear — and to the ~260 other apps it supports, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Square work happens whether or not anyone has a chat window open.

A few things that MCP can’t do but a Carly workflow can:

  • When a new payment lands in Square → create the customer in QuickBooks, add a row to the sales sheet, and post the total to the #sales Slack channel — automatically, the moment it happens.
  • Every morning → summarize yesterday’s Square sales, refunds, and top items and send the recap to the owner.
  • When an invoice goes unpaid past its due date → flag it, draft a reminder email for approval, and log the follow-up in your CRM.

The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the Square connection and everything downstream.

If you just want to interrogate your Square account from a chat, Square’s official MCP server is the right tool and it’s free to connect. If you want Square to actually do things — on a trigger, on a schedule, across every app an order or payment flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.

FAQ

Does Square have an official MCP server? Yes. Square (Block) maintains an official remote MCP server at mcp.squareup.com/sse, currently in beta, that gives approved MCP-compatible AI clients access to the full Square API — payments, orders, customers, catalog, invoices, bookings, and more. There’s also a local square/square-mcp-server option you can run yourself.

Is the Square MCP server free? Connecting the remote MCP is free; you’re authorizing an AI client against your existing Square account and scopes through OAuth. You still need whatever Square account and plan your data lives on, and less common AI clients may need to be approved on Square’s allowlist first.

Can the Square MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven Square work across apps, you need a workflow tool like Carly rather than an MCP server.

Can I connect Square to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Square for you and lets you build the automation in plain language — describe what you want to happen and it wires up the payments, orders, and customer data along with the other apps involved, with no server to host and no code to write.

Ready to automate your busywork?

Carly schedules, researches, and briefs you—so you can focus on what matters.

See what people say

"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.

Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.

On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."

Gus Ibrahim, Founder & Director, IHR