Integration · Company data

Connect Claude & ChatGPT to Danish addresses

Ask your AI to find the exact spelling of a Danish address, list the flats at a house number or match an old address to its current form. The tools use Adressevælger and Adressevask from Klimadatastyrelsen, published through Dataforsyningen, which replace DAWA for address search.

Connect Dataforsyningen (addresses) free

Free plan, no credit card. Takes about a minute.

Try asking

“Find the correct address for "sankt kjelds plads 11 kbh".”
The AI searches addresses and returns the official address text, Sankt Kjelds Plads 11, 2100 København Ø, with its id.
“Which flats are there at Rentemestervej 8, 2400?”
It finds the house number and lists every address at it with floor and door.
“Our customer list says Højgaardsvej 3, 4773 Stensved. Is that still right?”
It matches the old text to the current address and shows the former and current address text.

What your AI can do

Search addresses

Phonetic search in the Danish address register by free text or by street, number, postcode, floor and door.

Look up by id

Get an address or house number with status, postcode, street, municipality and entrance coordinates.

Clean up old addresses

Match an outdated or slightly wrong address text to one current address and see what changed.

“Which postcodes have a street called Rentemestervej?”
It searches street names and lists each postcode with the number of house numbers on that street.
“Give me the coordinates of the entrance to this address id.”
It looks up the address and returns the entrance point in the Danish EPSG:25832 grid.
“Check these five address ids and give me the full address texts.”
It fetches all the addresses in one call and lists their current texts and status.

8 tools for Dataforsyningen (addresses)

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

find_matching_addressMatch an old or slightly wrong address text to one current address. Returns the address id, the current text and the former text if the address has changed. Include the postcode.
get_addressGet one address by its id: address text, floor, door, status, postcode, street, municipality code and entrance coordinates (EPSG:25832).
get_addresses_by_idsGet several addresses at once by passing a comma-separated list of address ids in id_lokalids.
get_house_numberGet one house number by its id: address text, status, postcode, street, municipality and street code, and entrance coordinates (EPSG:25832).
list_addresses_at_house_numberList every address (each flat with floor and door) at one house number.
search_addressesSearch Danish addresses including floor and door. Pass free text in tekst (e.g. "Sankt Kjelds Plads 11 2100"), or vejnavn with husnummer, postnummer, etage and doer. Returns ids and full address texts.
search_house_numbersSearch Danish house numbers (street, number and postcode, without floor and door). Use when you only need the building entrance. Filter with kommunekode.
search_streetsFind a street name per postcode, including streets without addresses, with the number of house numbers on each.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Dataforsyningen (addresses) from the app list.
2
Paste your key
Enter adressevaelger123 as the token. Klimadatastyrelsen asks all users to send that token until personal user accounts for Adressevælger are introduced, expected late 2026 or early 2027. When you get your own token, replace it in PipMCP.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
Click your name, then Settings › Connectors › Add custom connector. Paste your link as the Remote MCP server URL. Switch it on from the + menu in a chat.

Questions

What can the AI do with Danish addresses?

It can search addresses, house numbers and street names, look up addresses and house numbers by id, list the addresses at a house number and match an old address text to the current address. All tools only read data.

Why not DAWA?

DAWA, the old address API on Dataforsyningen, closes on 1 October 2026. Klimadatastyrelsen built Adressevælger and Adressevask to replace its address search and address cleaning, so this app uses those.

Does the AI see my token?

No. The token is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on. All tools here only read public address data, and every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. Adressevælger is free to use. PipMCP is an independent service and is not affiliated with Klimadatastyrelsen or Dataforsyningen.