BumiAtlas MCP

Poland: EGiB cadastral parcels and sale prices

Polish cadastral parcels from GUGiK's EGiB open data, with sale prices from the RCN register, as tools an AI assistant can call: find a parcel by id_działki or coordinates, read its area, land-use classes and recorded sales, 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/poland

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-poland https://bumiatlas.com/mcp/poland

ChatGPT

Settings → Apps & Connectors → Advanced → Developer mode, then Create with the URL and OAuth authentication.

Cursor

in ~/.cursor/mcp.json

{
  "mcpServers": {
    "bumiatlas-poland": {
      "url": "https://bumiatlas.com/mcp/poland"
    }
  }
}

Tools

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

PL_parcel_search

Find Polish cadastral parcels (GUGiK EGiB) by id_działki or location, with each parcel's whole record and its recorded sales. query takes an id_działki ('040602_2.0008.66': TERYT unit, obręb and number) or coordinates as 'latitude, longitude' (e.g. 52.2297, 21.0122). Names aren't searchable: for a parcel known by obręb and number, search its coordinates or build the id from the TERYT unit code. With coordinates it returns parcels containing the point (distance 0), then the nearest within `radius` metres, closest first. Each parcel has id, num, obreb, obrebCode, jednostka, gmina, woj, area (registered, m²), klasouzytki, grupa (register group), attrs, data, transactions (up to 10 RCN sales: date, price and parcelPrice in PLN, seller and buyer types, use, zoning), mapArea and bbox. Set include_geometry for each boundary as GeoJSON (keep limit small). Use PL_parcel_image to see a parcel and its neighbours.

query*string: id_działki (040602_2.0008.66) or 'latitude, longitude'
radiusnumber: Search radius in metres around coordinates(default 25)
limitinteger: Maximum results(default 20)
include_geometryboolean: Include each boundary as a GeoJSON MultiPolygon(default false)

PL_parcel_image

A map image centred on a Polish parcel (id, its id_działki) 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, num, obreb, 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 a few metres are possible. 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: id_działki (040602_2.0008.66), 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

Which parcel is at 52.2297, 21.0122? Has it been sold?
Look up parcel 040602_2.0008.66.
What did the parcels around this point sell for?

About the data

A parcel's id_działki is its TERYT unit, obręb and number: 040602_2.0008.66. Names aren't searchable; search coordinates instead.
Sales list date, price (whole transaction and this parcel's share, PLN), seller and buyer types (never names), land use and zoning.
Registered area and land-use classes (klasoużytki) as the register writes them.