BumiAtlas MCP

Pakistan: Punjab urban parcels by PULSE code and housing society

Urban Punjab parcels from the PULSE project, as tools an AI assistant can call: find a parcel by its PULSE code, housing society or coordinates, read its plot number, land use and 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/pakistan

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

ChatGPT

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

Cursor

in ~/.cursor/mcp.json

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

Tools

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

PK_parcel_search

Find urban Punjab parcels (PULSE development-authority data) by parcel code, society name, or location, with each parcel's whole record. query takes a parcel code ('TXL-TEH-00C-000-0157-0000'; a prefix like 'MDT-TNS' lists that tehsil's or mouza's parcels), a housing society name or part of one ('DHA', 'Millat Town'), or coordinates as 'latitude, longitude' (e.g. 31.4726, 74.2728). With coordinates it returns parcels containing the point (distance 0), then the nearest within `radius` metres, closest first. Society and prefix searches list parcels paged with offset. Each parcel has id, uniParco, khasra (plot number), plotNo, block, sector, phase, society, source (which authority's layer), landuse, landuseSub, plotSize, area and mapArea (m²), anomaly (PULSE's data-quality flag), district, tehsil, division and bbox. Set include_geometry for each boundary as GeoJSON (keep limit small). Use PK_parcel_image to see a parcel and its neighbours.

query*string: parcel code or prefix ('TXL-TEH-00C-000-0157-0000', 'MDT-TNS'), society name ('DHA'), or 'latitude, longitude'
radiusnumber: Search radius in metres around coordinates(default 25)
limitinteger: Maximum results(default 20)
offsetinteger: Skip this many parcels of a society or code prefix, to page through them(default 0)
include_geometryboolean: Include each boundary as a GeoJSON MultiPolygon(default false)

PK_parcel_image

A map image centred on a Punjab parcel (id, or its uniParco code) or a point (query), with every parcel in view outlined and labelled with its khasra plot 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, uniParco, society, landuse, 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. PULSE linework is indicative: offsets of several metres from both imagery and the legal boundary 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: parcel id ('lda_schemes-148641') or uniParco code, 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 31.4726, 74.2728? What's its land use?
List parcels in DHA with their plot sizes.
Show parcel TXL-TEH-00C-000-0157-0000 on satellite imagery.

About the data

~878k plots in development-authority scheme areas and private housing societies of urban Punjab. No rural khasras, nothing outside Punjab.
A parcel code (uniParco) is tehsil, mouza, block, muraba, khasra and sub-khasra: TXL-TEH-00C-000-0157-0000. A prefix lists that level's parcels.
Indicative property lines only, not legal boundaries: no owner, title or price.