An MCP server, so an assistant can do the work
Lynkarr speaks the Model Context Protocol. Point Claude — or anything else that speaks MCP — at one URL, and the codes on your posters become something you can change by asking.
What MCP is, briefly
The Model Context Protocol is the standard way an AI assistant talks to a service that is not built into it: the server publishes tools, the assistant reads what each one does and calls the right one. Ours is hosted by us at https://lynkarr.com/mcp — nothing to install, nothing to keep running, and it takes the same API token the REST API does.
The thing it is actually for
A poster is printed. The campaign it points at has moved. Somebody says so, and the code now goes somewhere else — no reprint, no hunting through a dashboard, no risk of editing the wrong record because two are named similarly. Everything else an assistant can do here is convenience; repointing something already out in the world is the part that is genuinely hard any other way.
It cannot do more than a script could
Every tool is a call to the same public API, with the same token, scopes, rate limit and quota. There is no privileged path where the assistant is more capable than your own code, because there is no second implementation for one to hide in. An assistant given a read-only token is not shown the tools that would write — not shown rather than refused, so it cannot try, fail, and report that something is broken.
What it will not do
It cannot tell you who scanned anything, because nothing here records that. It cannot change your plan, your billing, your team or your account settings, and it cannot read what people submit through your forms. And it cannot repoint a static code, because a static code's destination is in the printed pattern — the tool says so rather than appearing to succeed.
What you can do with it
Ask for it in the words you would use anyway
“Point the autumn poster at the new landing page.” The assistant finds the code, changes the destination and tells you it is done. Nobody opens four screens to change one field.
It can only do what you ticked
You approve a connection on a page that lists, in plain words, exactly what it will be able to do. Read the codes but not change them, read the analytics but not the form responses — whatever you granted, and nothing else.
And three things it can never do
Invite or remove a person, change anybody’s role, or touch your billing. Those are refused by the API itself rather than by policy, so they hold for every assistant, every token and every scope you could possibly grant.
Getting there
-
Make an API token
Settings, then API tokens. Only needed for a client that cannot sign in — most can, and then there is no token to make.
-
Choose what it may do
Read-only is codes:read, links:read and analytics:read. Add the write scopes only if you want the assistant to create and repoint. Signing in shows you the same list before you agree to it.
-
Add the server
In your assistant, add a remote MCP server at https://lynkarr.com/mcp, then sign in when it asks. A client that cannot sign in takes the token as an X-API-Key header instead.
-
Ask it something
“List my QR codes” proves the connection. “Point the autumn poster at the new page” proves the point.
More in the same place
Questions
What is an MCP server?
MCP — the Model Context Protocol — is the standard way an AI assistant talks to a service it does not have built in. An MCP server publishes tools the assistant can call. Lynkarr's is a remote one at https://lynkarr.com/mcp: nothing to install, authenticated with a normal Lynkarr API token.
Which assistants can connect to it?
Anything that supports remote MCP servers over HTTP. Claude does, and the setting is usually called connectors, integrations or MCP servers. Because it is a standard rather than an integration we built for one product, a client that speaks MCP works without us doing anything.
Do I need an API token to connect an assistant?
Not usually. Most MCP clients will offer to sign in, and that is the easier route: you are sent to Lynkarr, shown exactly what the assistant is asking to do, and you allow or refuse it. Nothing is copied and no token is typed. A client that has no sign-in step takes an API token as an X-API-Key header instead — use that header rather than Authorization, because a client that manages its own sign-in tends to treat Authorization as its own and quietly drop a custom one. Either way the connection appears in Settings, API tokens and revoking it there disconnects the assistant. The step-by-step for Claude, ChatGPT, Copilot, Cursor and VS Code is in the support article.
Can an AI assistant change where a QR code I have already shared points?
Yes, if you give its token the codes:write scope. That is the case worth connecting it for: the pattern does not change, so every copy already out there — on a pack, in a signature, on a slide — keeps working and starts going somewhere new. Static codes cannot be repointed by anyone, including you, because the destination is in the pattern.
Is it safe to connect an assistant to my account?
It is exactly as capable as the token you give it, and no more — every tool is a call to the same public API with the same scopes and limits. Start with a read-only token. Three things no token can ever do, whatever scopes it holds: invite or remove a person, change a role, or touch your billing. Team access is read only by design, because those are what turn a leaked token into a lost account.
Can an assistant read what people submit through my forms?
Only with forms:read, and only if you grant it. That scope covers form submissions and the enquiries sent through a digital card, because reading the responses is most of what a form is for — so it is a meaningful thing to tick rather than a side effect of letting an assistant tidy up your form titles. Both are read only: nothing can delete somebody's enquiry.
Does the MCP server cost extra?
No. It is available on every plan including the free one, and it uses your normal API allowance rather than a separate one.
Try it with one code
The free plan has no expiry and asks for no card, and the analytics behind it are the same ones a paying customer gets.
Free forever for one person. No card, and 10,000 scans a month included.