QR Codes in Claude and ChatGPT

Manage your QR codes by asking an AI assistant

Connect Claude, ChatGPT or any MCP client to your account and your codes become something you can talk to. Ask which poster is working, re-point a printed code at the new menu, or create one from a sentence — without opening a dashboard.

Try it — start free A scan analytics dashboard: a rising bar chart next to a world map dotted with scan locations.

What MCP is, in one paragraph

MCP — the Model Context Protocol — is an open standard for letting an AI assistant talk to a service on your behalf. You paste a URL and a token into the assistant once, and from then on it can call a fixed set of operations that service has published. It is not a plugin, a browser automation, or the assistant "having your password": it is a defined list of things it may do, and nothing outside that list is reachable.

Anthropic published it and it has been adopted well beyond Claude — ChatGPT, Cursor, Windsurf, Zed and others all speak it. Which means one connection here works with whichever assistant you already use, and keeps working if you switch.

Why this is a better fit for QR codes than most things

A dynamic QR code has one property that makes it unusually well suited to being managed by conversation: the expensive part already happened. The code is printed. It is on a poster, a menu, a bag, a window. What remains is a small number of decisions about where it should point and whether it is on — and those are exactly the decisions that are annoying to make through a dashboard, because they are quick, occasional, and always come up when you are doing something else.

"The autumn menu is up, point the table codes at it" is one sentence. Through a dashboard it is a login, a search, a form and a save, times however many table codes there are. The dashboard is not badly built; the task is just badly shaped for a dashboard.

What the connection can and cannot reach

An assistant connected to your account can read your codes, folders and scan analytics, create codes, change where a code points, and pause or resume one. That is the entire list.

It cannot delete anything — there is no delete operation published, so this is a property of the connection rather than a promise about behaviour. It cannot see or change your password, your billing details or your subscription. It cannot reach another customer’s account: every operation runs against your own records, so somebody else’s code is not "refused", it simply does not exist as far as your connection is concerned.

Every assistant you connect gets its own named token, and each shows up on your dashboard with what it is and when it last did anything. Revoking one takes effect on the next request it makes.

The scan numbers it quotes are the same ones you see

An assistant reading different figures from the ones on your own screen would be worse than useless, so it does not: the analytics it reports come from the same code that draws your dashboard, over the same periods.

That includes the bot filtering. Link previews, crawlers, uptime monitors and prefetches are excluded from every count, and reported separately when asked, so a quiet week has an explanation rather than just a smaller number.

What an assistant can do with your account

What the feature actually does, part by part.

Re-point a printed code

The one that matters. "Point the café menu code at the new PDF" takes effect for every copy already printed, within seconds.

Ask about scans

Which code did best this month, which have never been scanned, what the device and country split looks like — in a sentence, not a filter.

Create codes

A name, a destination, a folder, optionally a custom short link. It comes back with the short URL ready to print.

Pause and resume

Take a code out of service while a page is broken and put it back afterwards. Nothing is deleted either way.

It cannot delete anything

By design, not by policy. There is no delete tool on the connection at all, so no misread sentence can remove a code from a poster.

Revocable in one click

Each assistant gets its own named token. Revoking one stops it immediately and leaves the others working.

Built for

Anyone whose codes are already printed and whose destinations are not.

Restaurants changing menus Agencies managing client codes Events with printed signage Retail promotions Anyone with codes already printed Developers who live in an editor

Connect an assistant in about two minutes

Once per assistant. It stays connected afterwards.

1

Open AI Assistants in your dashboard and create a token, named after where it will live.

2

Copy the token — it is shown once, because only a one-way hash of it is stored.

3

In your assistant, add a custom MCP connector pointing at our endpoint with that token as a bearer header.

4

Ask it something: "which of my QR codes got scanned this week?"

5

Check the AI Assistants page — the assistant appears there the moment it first connects.

Which plans include this

Taken from the live plan matrix, so this page and your account always agree.

Free
Not included
Normal
Not included
Pro
Not included
Teams
Included

See the full plan comparison for everything each tier includes.

Questions people ask

Straight answers to what usually decides whether this is the right tool for the job.

Which AI assistants does this work with?
Any client that speaks MCP, which now covers Claude (both the desktop and web apps and Claude Code), ChatGPT, Cursor, Windsurf, Zed, Cline and a growing list of others. You are connecting to an open protocol rather than to one vendor, so the same setup works with whichever you use and survives you switching.
Can the assistant delete my QR codes?
No, and not as a matter of policy — there is no delete operation on the connection at all. The assistant is offered a fixed list of things it can do, and removing a code is not on it. Deleting is done by you, in the dashboard, where there is a trash you can restore from for 30 days.
Is it safe to give an AI assistant access to my account?
The connection is deliberately narrow: reading your codes and analytics, creating codes, re-pointing them, pausing them. It cannot reach your password, your billing details or anyone else’s account, and it cannot delete. Each assistant gets its own named token you can revoke on its own, and your dashboard shows what is connected and when it was last active.
Does re-pointing a code through an assistant work the same as doing it myself?
It is the same change, through the same code path. Every copy of that QR code already printed starts going to the new destination within seconds, the image does not change, and the short URL stays the same.
Which plans include it?
AI assistant access is on the Pro and Team plans. Tokens you have already created keep their place if a plan lapses — they stop working, they are still listed, and you can still revoke them; upgrading again makes them work without any change at your end.
Do I need to be a developer to set this up?
No. In Claude it is a settings screen: add a custom connector, paste a URL and a token. In editors and some other clients it is a small block of JSON we give you ready to copy. The setup guide walks through each one.

Ready to stop clicking through a dashboard?

Free plan available forever. No credit card required. Get started in under 60 seconds.

Try it — start free