← All BumiAtlas MCP endpoints

BumiAtlas MCP

Benin: ANDF cadastral parcels and declared zones

Beninese cadastral parcels from the ANDF national cadastre, as tools an AI assistant can call: find a parcel by NUP, titre foncier or coordinates, read its register status, right and open survey issues, 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/benin

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-benin https://bumiatlas.com/mcp/benin
ChatGPT
Settings → Apps & Connectors → Advanced → Developer mode, then Create with the URL and OAuth authentication.
Cursor
in ~/.cursor/mcp.json
{
  "mcpServers": {
    "bumiatlas-benin": {
      "url": "https://bumiatlas.com/mcp/benin"
    }
  }
}

Tools

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

BJ_parcel_search
Find Beninese cadastral parcels (ANDF national cadastre) by NUP, titre foncier number or location, with each parcel's whole record. query takes a NUP or titre foncier number (narrow it with commune), or coordinates as 'latitude, longitude' (e.g. 6.3654, 2.4183). With coordinates it returns parcels containing the point (distance 0), then the nearest within `radius` metres, closest first, and the declared zones containing the point (type, designation, displayName, commune, surface in m², source). Each parcel has id, nup, register, right, baUnitType, nature, titleNumber, titleCommune, projectCode, localCode, partyExists, calculatedArea and surveyedArea (m²), departement, commune, arrondissement, quartier, shortcoming, mapArea and bbox. Set include_geometry for each boundary as GeoJSON (keep limit small). Use BJ_parcel_image to see a parcel and its neighbours.
query*string
NUP, titre foncier number, or 'latitude, longitude'
communestring
Commune name (Cotonou), to narrow a number
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)
BJ_parcel_image
A map image centred on a Beninese parcel (id, from BJ_parcel_search) or a point (query), with every parcel in view outlined and labelled with its NUP, 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, nup, commune, 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
Parcel id (the spatial-unit id from BJ_parcel_search), 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