BumiAtlas MCP

Rwanda: LAIS registered parcels by UPI

Rwanda's registered land parcels from the National Land Authority's LAIS, as tools an AI assistant can call: find a parcel by UPI, admin area or coordinates, read its recorded area and location, 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/rwanda

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

ChatGPT

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

Cursor

in ~/.cursor/mcp.json

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

Tools

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

RW_parcel_search

Find Rwandan land parcels (NLA LAIS) by UPI, admin area or location, with each parcel's whole record. query takes a UPI ('1/02/09/02/9430') or coordinates as 'latitude, longitude' (e.g. -1.9441, 30.0619); or leave it out and pass district (and sector, cell, village) to list an area's parcels, paged with offset. With coordinates it returns parcels containing the point (distance 0), then the nearest within `radius` metres, closest first. Each parcel has upi, province, district, sector, cell, village, size (recorded, m²), areaInWetland, mapArea and bbox. Set include_geometry for each boundary as GeoJSON (keep limit small). Use RW_parcel_image to see a parcel and its neighbours.

querystring: UPI (1/02/09/02/9430) or 'latitude, longitude'
districtstring: District name (Gasabo), to list its parcels
sectorstring: Sector name, within the district
cellstring: Cell name, within the sector
villagestring: Village name, within the cell
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)

RW_parcel_image

A map image centred on a Rwandan parcel (id, its UPI) or a point (query), with every parcel in view outlined and labelled with its parcel number (the UPI's last part), 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, parcel, 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. The registration was traced on imagery, so offsets of a few metres are normal. 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: UPI (1/02/09/02/9430), 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 -1.9441, 30.0619? What is its UPI?
Look up UPI 1/02/09/02/9430.
List the parcels in Kimironko sector, Gasabo.

About the data

All ~11.7M parcels from the 2009–2013 systematic registration of the whole country.
A UPI is province/district/sector/cell/parcel: 1/02/09/02/9430.
No owners, titles or prices.