AIProperty Phuket

Live Phuket, Thailand real-estate catalogue: ~5,800 homes for sale and ~7,800 long-term rentals across 15 zones, plus development projects.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Search Properties: Structured search of Phuket properties for sale with hard filters. Full parity with the website catalog filter. district, property_type, view, ownership and completion accept a sing
  • Semantic Search: Semantic search over the catalog + Voyage knowledge base (~17k chunks). Listings are searched DIRECTLY against the vector index here (no rate limit, full completeness + pagination, mu
  • Get Property: Full details for a single listing by its id (e.g. from search results). Returns the listing's attributes plus fazwaz_id, fazwaz_url (canonical source link) and the public site url. Price

What data it sees

Do you need an account

No: the server works without sign-in

Live Phuket, Thailand real-estate catalogue: ~5,800 homes for sale and ~7,800 long-term rentals across 15 zones, plus development projects. Structured and semantic search, per-listing detail, and an enumerable district/filter vocabulary so models query the real option space instead of guessing.

How to connect

How to connect AIProperty Phuket to Claude

The server address to paste into Claude settings:

https://aiproperty-phuket--fastlyhouse.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect AIProperty Phuket to ChatGPT

The server address to paste into ChatGPT settings:

https://aiproperty-phuket--fastlyhouse.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect AIProperty Phuket to Cursor

The server address to paste into Cursor settings:

https://aiproperty-phuket--fastlyhouse.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (5)

Raw names from tools/list. Only developers need these.

search_propertiesStructured search of Phuket properties for sale with hard filters. Full parity with the website catalog filter. district, property_type, view, ownership and completion accept a single value, a comma-string, OR an array, and (district/type) are normalized: zone names map to slugs ("Rawai"->rawai), type synonyms collapse to the catalog vocab ("Villas"->Villa). Multi-value = OR. Args: query: Free-text match on title / project / location / id. district: Zone(s) — "rawai", "Nai Harn", ["rawai","nai-harn"], "rawai,kata". property_type: Villa, House, Townhouse, Condo, Apartment, Penthouse (arrays/ synonyms/plurals/any case ok). bedrooms: "1,2" or "4+" or ["2","3"] (Studio = "0"). min_price / max_price: Price bounds in THB. min_area / max_area: Floor-area bounds in sqm. min_price_per_sqm / max_price_per_sqm: ฿/sqm bounds (THB). min_floor / max_floor: Floor-level bounds. min_beach / max_beach: Distance-to-beach bounds in KM (e.g. max_beach=1 = within 1 km of a beach). listing_age: Freshness window — "2w", "2m", "6m", "1y", or "old" (>1y). view: e.g. "Sea View","Pool View","Mountain View" (single/comma/array). ownership: "Foreign Ownership","Thai Ownership","Company","Leasehold" (single/comma/array). furnished: "Furnished", "Partly Furnished" or "Unfurnished". completion: "Off Plan","Completed","Under Construction","Assignment" (array ok). investment_profile: "str" (short-term rental), "ltr" (long-term), "luxury". sort: newest | price_asc | price_desc | area_asc | area_desc | sqm_asc | sqm_desc. page: 1-based page index. Iterate up to `pages` to enumerate ALL matches. limit: Page size (max 100). Returns {total, page, pages, applied_filters, results[], warnings?, diagnostics?}. Each result has fazwaz_id, fazwaz_url, public url, and price in THB.
semantic_searchSemantic search over the catalog + Voyage knowledge base (~17k chunks). Listings are searched DIRECTLY against the vector index here (no rate limit, full completeness + pagination, multi-zone OR). Knowledge sources (projects/developers/guides/districts) are answered via the RAG endpoint. Two modes (both paginate): - mode="rerank" (default): Voyage rerank-2 over the nearest candidates → best-by-meaning ordering. Best for "show me the most relevant few". - mode="filter": COMPLETENESS — every hard-filter match, ranked by similarity, no rerank trim, with `min_score` + `page`/`top_k` paging. For a guaranteed-exhaustive list also consider `search_properties`. district / property_type accept a value, comma-string or array and are normalized (incl. multi-zone OR), exactly like search_properties. Args: query: Natural-language query (EN or RU). sources: Defaults to ["listings"]. Add "projects","developers","guides", "districts" to also pull knowledge chunks (answered via RAG). Use "sales_kb" for the internal sales playbook — funnel stages, reply scripts, objection handling and the buying-procedure (for drafting client replies / consulting on next steps). mode: "rerank" | "filter". top_k: Page size. page: 1-based page. min_score: 0..1 similarity cutoff. district/property_type/bedrooms/min_price/max_price: hard filters. Returns {query, mode, total, page, pages, applied_filters, results[], knowledge?[], notes?[]}. Listing results carry fazwaz_id, fazwaz_url, public url; prices in THB.
get_propertyFull details for a single listing by its id (e.g. from search results). Returns the listing's attributes plus fazwaz_id, fazwaz_url (canonical source link) and the public site url. Prices are in THB. Returns {error:"not_found"} if the id does not exist.
list_districts_and_filtersReference data for building searches: districts (with listing counts) and the set of valid filter values (property types, bedrooms, views, ownership, price bounds). Call this first when unsure which filter values are valid.
search_by_projectAll units of one development (condo/villa project), with optional filters. Resolve by `project_id` (exact) or `project_name` (e.g. "Nai Harn Beach Condominium", "The Deck Patong"). Matches BOTH the project FK and the free-text project field, so text-only-linked units are not missed. If a name is ambiguous, returns candidate projects to pick from. Args: project_name: Development name (fuzzy, case-insensitive). project_id: FazWaz project id (from a prior candidates list / list tools). bedrooms: "2", "4+" or ["2","3"]. min_price / max_price: THB bounds. page / limit: Pagination (limit max 100). Iterate up to `pages` for all. Returns {project_id, project, total, page, pages, results[]} or {error:"ambiguous_project", candidates[...]} / {error:"not_found"}.