← All BumiAtlas MCP endpoints

BumiAtlas MCP

Croatia: DGU cadastral parcels by KO and number

Croatian cadastral parcels from the State Geodetic Administration's cadastre, as tools an AI assistant can call: find a parcel by katastarska općina and number or coordinates, read its registered area, and see it on a map with its neighbours.

Server URL

Streamable HTTP with OAuth. The first time you connect, your client opens a browser window to sign in with Google; no API key needed.

https://bumiatlas.com/mcp/croatia

Connect

Claude (claude.ai, desktop)
Settings → Connectors → Add custom connector, paste the URL, then Connect and sign in with Google.
Claude Code
claude mcp add --transport http bumiatlas-croatia https://bumiatlas.com/mcp/croatia
ChatGPT
Settings → Apps & Connectors → Advanced → Developer mode, then Create with the URL and OAuth authentication.
Cursor
in ~/.cursor/mcp.json
{
  "mcpServers": {
    "bumiatlas-croatia": {
      "url": "https://bumiatlas.com/mcp/croatia"
    }
  }
}

Tools

Tool names and descriptions are in English, which models understand best; your assistant still answers in your language.

HR_parcel_search
Find Croatian cadastral parcels (DGU cadastre) by KO and parcel number, id or location, with each parcel's whole record. query takes a national reference ('300128-1509'), a KO code with the number ('KO 300128 1509'), a KO name with it ('Ada 1509', 'k.o. Ada, k.č. 308/5'), a KO code alone (lists its parcels, paged with offset), a parcel id ('CP.39262347'), or coordinates as 'latitude, longitude' (e.g. 45.8150, 15.9819). With coordinates it returns parcels containing the point (distance 0), then the nearest within `radius` metres, closest first. Each parcel has id, ref, ko, koName, num, area (registered, m²), since, mapArea and bbox. Set include_geometry for each boundary as GeoJSON (keep limit small). Use HR_parcel_image to see a parcel and its neighbours.
query*string
'300128-1509', 'Ada 1509', a KO code, 'CP.39262347', or 'latitude, longitude'
radiusnumber
Search radius in metres around coordinates(default 25)
limitinteger
Maximum results(default 20)
offsetinteger
Skip this many matches of a number or name search, to page through them(default 0)
include_geometryboolean
Include each boundary as a GeoJSON MultiPolygon(default false)
HR_parcel_image
A map image centred on a Croatian parcel (id, 'CP.39262347' from HR_parcel_search) or a point (query), with every parcel in view outlined and labelled with its number, so you can see which parcel is where. The parcel passed as id is drawn in red with a larger label; a query point is a red dot. Returns the parcels in view as JSON (label, id, ref, num, area in m²; labelled: false where its label didn't fit), then one JPEG per basemap. Basemaps: satellite (Esri World Imagery, often a few years old), hybrid (the same imagery with road and place names), streets and topo (Esri's street and topographic maps). Pass several to compare, e.g. ['satellite', 'streets'] to match buildings with street names. Parcel outlines are yellow on imagery and magenta on maps. Imagery is not always aligned with the cadastre: offsets of several metres are common in older surveys. A scale bar is at bottom left. Labels are left off where they'd overlap; call again with a smaller radius to read them. Each image costs about as much context as 1,000 words, so ask for what you need.
idstring
Parcel id (CP.39262347), drawn in red
querystring
'latitude, longitude' to centre on instead of a parcel
radiusnumber
Metres from the centre to the image edge. Default: fits the parcel with a margin, or 80 m around a point
basemapsarray
One image per basemap(default ["satellite"])
sizeinteger
Image width and height in pixels(default 768)

Try asking

About the data