Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@arnfa-mcp plan a weather-fit day in Bangkok tomorrow"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for Arnfa — weather-aware trip planning across Thailand. Lets any AI agent read the Thai sky and plan a weather-fit day in 150+ areas (Bangkok neighbourhoods & districts, all 76 province cities, tourist hotspots).
Reads Arnfa's open API — no key, no fabrication (real forecast or an honest error).
arnfa_list_areas(query?, tier?) — find a valid area key (search by Thai/English name).
arnfa_plan_day(area, budget?, day?) — an ordered, weather-fit itinerary; day 0–6 plans ahead.
arnfa_sky_now(area) — current sky + a go-out verdict for one area.
arnfa_where(day?) — rank WHERE the sky is clearest across Thailand ("ไปไหนดี").
arnfa_cooling_centers(lat, lng, n?) — nearest official Bangkok cooling refuges (ห้องหลบร้อน) for dangerous heat / PM2.5.
arnfa_ask(message, prior?) — ask in natural Thai/English; the grounded engine reads the real sky and narrates a plan. Pass back the previous reply's intent as prior to refine (multi-turn).
Related MCP server: Travel Planner MCP Server
npx arnfa-mcp # runs the stdio MCP server, no installWire into a client (e.g. Claude Code .mcp.json):
{ "mcpServers": { "arnfa": { "command": "npx", "args": ["-y", "arnfa-mcp"] } } }npm install && npm run build
node dist/index.js # stdio MCP server
ARNFA_BASE=http://localhost:3248 npm run smoke # quick check against a deploymentARNFA_BASE (default https://arnfa.vercel.app) points the tools at any Arnfa deployment.
MIT.
Ask Arnfa AI in natural Thai or English — it reads the REAL sky and returns a weather-fit plan (the same grounded engine, narrated). For a follow-up that refines the last plan, pass back the intent from the previous reply as prior.
Inputs: message (required), prior.
Nearest OFFICIAL Bangkok cooling centers (ห้องหลบร้อน) to a point — for dangerous heat or PM2.5. Real กทม. open data.
Inputs: lat (required), lng (required), n.
List/search Arnfa's plannable areas across Thailand (Bangkok neighbourhoods & districts, all 76 province cities, tourist spots) with real POI counts. Use to find a valid area key.
Inputs: tier, query.
Plan a weather-fit day in an area: the engine reranks real places by the forecast at each arrival time and returns an ordered itinerary. Real forecast only — never fabricated.
Inputs: area (required), day, budget.
Current sky + a go-out verdict for an area (real forecast at its centre).
Inputs: area (required).
Rank WHERE the sky is clearest across Thailand for a chosen day — the 'ไปไหนดี / where should I go' view. One bulk real forecast, never fabricated.
Inputs: day.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Most tools have clearly distinct purposes, but arnfa_plan_day and arnfa_ask both produce weather-fit plans, which could cause confusion. However, the descriptions clarify that one is a direct structured planner and the other is an AI-narrated follow-up, so the overlap is manageable.
While all tools share the 'arnfa_' prefix, the naming conventions vary: 'list_areas' and 'plan_day' use verb_noun, but 'sky_now' uses noun_adverb, 'where' is just an adverb, 'cooling_centers' is a noun phrase, and 'ask' is a bare verb. This mixed style is readable but lacks a consistent pattern.
With 6 tools covering area discovery, planning, current sky, location ranking, emergency cooling centers, and natural language queries, the count is well-scoped for the intended functionality. Each tool earns its place without unnecessary bloat or sparseness.
The tool surface covers core workflows: finding areas, planning a day, checking current conditions, choosing the clearest location, and getting emergency centers. The only minor gap is the lack of a direct multi-day forecast tool, but agents can work around it by using plan_day for specific dates.
Your personal AI travel concierge — flights, hotels, 116M+ POIs, visas, weather & more
Real-time data API for AI Agents: stocks, weather, forex, logistics, search, scrape, news, IP.
Flight and sky conditions for agents, from METAR/TAF and airports to aurora and satellite passes.
Travel tools for AI agents: plan and edit real trips, search stays and tours, import travel videos.
