Thailand: DOL parcels and public land, comprehensive-plan zoning

Settings → Connectors → Add custom connector, paste the URL, then Connect and sign in with Google.

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

in ~/.cursor/mcp.json

Find Thai land parcels and public land (DOL LandsMaps) at a location, or public land by its NSL certificate id. query takes coordinates as 'latitude, longitude' (e.g. 13.8231, 100.5100), or an NSL id (province abbreviation + number, e.g. UB5004). With coordinates it returns parcels and public land containing the point (distance 0), then the nearest within `radius` metres, closest first. To search an address, geocode it first; a radius of 25–100 m helps with geocoded points. Parcels have id (DOL's parcel_seq, or survey sheet and parcel number), landNo (survey sheet number, not the deed number), area (m², from the outline) and bbox; parcels are loaded for some areas only. Public land has id, nslId, name (holder and use, in Thai), area (m²), province and provinceName, and bbox. There is no search by deed number or owner: the public data has neither. Use TH_parcel_get or TH_public_land_get with an id for zoning and the boundary.

One Thai parcel by id (DOL's 20-digit parcel_seq or survey-sheet id like 5036-2-4806-15-120, from TH_parcel_search): landNo (survey sheet number, not the deed number), area (m², computed from the outline: DOL's public layer has no recorded area) and zona, the comprehensive-plan zones covering it, largest share first: landUse with landUseEn, use (DPT code), plan, planLevel (town, province or bangkok) and share of the parcel (0–1). Where a town plan covers the parcel, the province plan's zones are left out. Zones covering under 5% are left out too. Set include_geometry for the boundary as GeoJSON.

One plot of Thai public land with an NSL certificate (นสล.) by id (from TH_parcel_search): nslId, name (holder and use in Thai, e.g. กระทรวงมหาดไทย (ป่าช้าสาธารณประโยชน์) = Ministry of Interior, public cemetery), area (m², from the certificate's rai-ngan-wa), survey scale, UTM map sheet and parcel number, moo (village number), village, tambon, amphoe, province and provinceName, office (responsible land office), and zona, the comprehensive-plan zones covering it (as in TH_parcel_get). Set include_geometry for the boundary as GeoJSON.

Comprehensive-plan (ผังเมืองรวม) land-use zoning at a location in Thailand, or one zone by id. Pass query as 'latitude, longitude' (e.g. 13.7563, 100.5018), or id. Each zone has id, plan (DPT's plan code; xx00000 is a province-wide plan) and planName, planLevel (town, province or bangkok), province and provinceName, landUse (RESIDENTIAL_LOW, COMMERCIAL, INDUSTRY, COMMUNITY, RURAL_AGRICULTURE, …) with landUseEn, use (DPT land-use code), block, Bangkok's zone and subZone (Thai numerals), far (floor area ratio), bcr (building coverage ratio), osr (open space ratio, %), maxHeight (m), minLot (m²), and area (m², the whole zone polygon). Empty fields are left out. Town plans come first: where one covers the point it applies, and the province plan's COMMUNITY zone under it only marks the town. An empty result means no plan is loaded there.

A map image centred on a Thai parcel (id, DOL's parcel id from TH_parcel_search) or a point (query), with every parcel in view outlined and labelled with its land number (landNo, from the survey sheet, not the deed 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: the land number, with /2 on a repeated one and #n on parcels without one; id, landNo, area in m² from the outline; labelled: false where its label didn't fit), then one JPEG per basemap. Public land isn't drawn. 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. Parcels are only loaded for some areas, so elsewhere the image has none. Imagery is not always aligned with DOL boundaries: 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.