au-weather-mcp

au-weather-mcp

Provides LLMs with real-time, historical, and forecast Australian weather data via Open-Meteo, using plain-English location keys and fuzzy search.

Category
Visit Server

README

au-weather-mcp

tests PyPI Python License: MIT

Ask Claude about Australian weather and air quality and get real, current numbers — not "I don't have access to that data." This MCP server gives Claude (and other MCP clients like Cursor) live access to Australian weather + air-quality data via Open-Meteo, which aggregates Bureau of Meteorology observations under licence. 45 curated locations (every state capital + every regional centre over ~25k), postcode and place-name lookup, current observations, 16-day forecasts, 80+ years of historical data, and multi-location comparison.

Companion to abs-mcp (ABS macro stats), rba-mcp (Reserve Bank), and ato-mcp (tax + charity register) — together the four cover Australia's most-asked public data.

What you can ask

Once installed, your LLM can answer questions like:

Question Real response
What's the weather in Sydney right now? Current temperature, humidity, wind, rain, pressure with the time stamped
Forecast for Melbourne next week? 7-day daily forecast with max/min temps and rain
How was Sydney summer in January 2020? Historical daily data from Open-Meteo's archive (1940+)
Compare rainfall in Cairns vs Brisbane this year Multi-location queries with provenance per row
Tropical Queensland weather today Search fuzzy by region/state/description

Every response carries a CC-BY 4.0 attribution string and a direct Open-Meteo URL the agent can cite back to the user.

Why Open-Meteo (not BOM directly)

BOM publishes their own JSON/XML endpoints, but they actively 403 non-browser User-Agents and have no documented commercial-use path below their ~$5k/yr Registered User Service. Open-Meteo:

  • Aggregates BOM data under their existing licensing arrangements with national meteorological services
  • Free tier is explicit and generous; commercial use is $30/mo with public terms
  • Returns clean, versioned, schema-stable JSON with units alongside every value
  • Covers historical data back to 1940 via their archive endpoint
  • No API key, no User-Agent gymnastics

We attribute both Open-Meteo and BOM in every response.

Install

# After publish:
uvx au-weather-mcp

# Local dev:
uv pip install -e .

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "weather": {
      "command": "uvx",
      "args": ["--upgrade", "au-weather-mcp"]
    }
  }
}

The --upgrade flag makes uvx re-check PyPI on each Claude Desktop launch, so bug fixes propagate without manual cache refresh. Costs ~100ms at startup.

For a local checkout (before PyPI publish):

{
  "mcpServers": {
    "weather": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/au-weather-mcp", "au-weather-mcp"]
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "weather": {
      "command": "uvx",
      "args": ["--upgrade", "au-weather-mcp"]
    }
  }
}

Tools

Tool What it does
search_locations(query, limit=10) Fuzzy-search the 45 curated AU locations by name, state, or description.
describe_location(location) Lat/lng, timezone, elevation, nearest BOM station, and the canonical Open-Meteo URL.
latest(location) Current weather observation — temp, humidity, wind, rain, pressure. 15-min cache.
get_weather(location, start_date, end_date, granularity) Time-series query. Auto-routes to historical archive (1940+) or forecast (today + 16 days). Daily or hourly granularity.
air_quality(location) Current PM2.5, PM10, ozone, NO₂, SO₂, CO + European & US AQI with plain-English labels. (v0.4.0)
compare_locations([locs]) Side-by-side current weather for 2–10 locations in one call. Fans out concurrently. (v0.4.0)
list_curated() All 45 supported location IDs.

Accepts almost any input shape

The location parameter on every tool resolves six different input shapes — agents and users don't need to know the curated key format:

Input shape Example Resolves via
Curated ID "sydney", "gold_coast" Direct curated lookup (fast)
Place name, any case "Sydney", "Gold Coast", "GOLD COAST" Normalised curated lookup
State code or full name "NSW", "Queensland", "Western Australia" State → capital alias
Raw coordinates "-33.87,151.21" Direct lat/lng (AU bbox enforced)
AU postcode "2026" (Bondi Beach), "4217" (Gold Coast), "6160" (Fremantle) OpenStreetMap Nominatim
Any AU place name "Byron Bay", "Margaret River", "Toowoomba" Open-Meteo geocoding (AU-filtered, population-sorted)
Typo of a curated name "Sydny", "Melbourn" High-confidence fuzzy match

Every response includes a location_resolution field with one of curated, state_alias, raw_coordinates, geocoded, or fuzzy_curated — so the agent (and the user) can see HOW the input was interpreted.

Curated locations

45 curated locations covering all 8 state/territory capitals plus 37 major regional centres (every AU population centre over ~25k). Anything outside the curated set still works via the place-name geocoder or postcode lookup.

Region Locations
Capitals (8) sydney · melbourne · brisbane · perth · adelaide · hobart · darwin · canberra
NSW regional (10) newcastle · wollongong · tamworth · wagga_wagga · albury · orange · bathurst · dubbo · coffs_harbour · port_macquarie
QLD regional (9) gold_coast · sunshine_coast · cairns · townsville · mackay · toowoomba · rockhampton · bundaberg · hervey_bay
VIC regional (6) geelong · ballarat · bendigo · mildura · shepparton · warrnambool
WA regional (5) broome · bunbury · geraldton · albany · kalgoorlie
SA regional (2) mount_gambier · whyalla
TAS regional (3) launceston · devonport · burnie
NT regional (2) alice_springs · katherine

Coordinates are anchored to the canonical BOM observation point for each city (e.g. Sydney = Observatory Hill, Melbourne = Olympic Park) so cross-checking against BOM's official observations is straightforward. See src/au_weather_mcp/data/curated/locations.yaml for the full registry.

Worked examples

"What's the weather in Sydney right now?"

latest(location="sydney")

Returns:

{
  "location_id": "sydney",
  "location_name": "Sydney",
  "state": "NSW",
  "latitude": -33.8607,
  "longitude": 151.205,
  "timezone": "Australia/Sydney",
  "period": {"start": "2026-05-12T11:30", "end": "2026-05-12T11:30"},
  "current": {
    "time": "2026-05-12T11:30",
    "temperature_c": 19.7,
    "apparent_temperature_c": 18.1,
    "relative_humidity_pct": 67,
    "precipitation_mm": 0.0,
    "cloud_cover_pct": 43,
    "pressure_msl_hpa": 1034.5,
    "wind_speed_kmh": 18.4,
    "wind_direction_deg": 149,
    "wind_gusts_kmh": 43.2,
    "weather_code": 1,
    "weather_description": "Mainly clear"
  },
  "source": "Open-Meteo (aggregates Bureau of Meteorology data under licence)",
  "attribution": "Weather data by Open-Meteo.com (https://open-meteo.com), licensed under CC BY 4.0...",
  "source_url": "https://api.open-meteo.com/v1/forecast?latitude=-33.8607&...",
  "server_version": "<package version, e.g. 0.3.3>",
  "location_resolution": "curated",
  "location_input": "sydney"
}

"How was Sydney in January 2020?"

get_weather(
  location="sydney",
  start_date="2020-01-01",
  end_date="2020-01-31",
  granularity="daily"
)

Returns 31 DailyAggregate rows with temperature_max_c, temperature_min_c, precipitation_sum_mm, and weather descriptions per day.

"7-day Melbourne forecast, hourly detail"

get_weather(
  location="melbourne",
  start_date="2026-05-12",
  end_date="2026-05-19",
  granularity="hourly"
)

Returns 168 hourly rows.

Date formats

start_date and end_date must be YYYY-MM-DD. The server validates both the regex and the semantic date — 2024-13-40 raises a clean ValueError rather than silently failing.

Date range Routes to Coverage
end_date >= today - 5 days Open-Meteo forecast endpoint Today + 16 days
end_date < today - 5 days Open-Meteo historical archive 1940-01-01 onwards

Trust contract

Every response carries:

  • source_url — the exact Open-Meteo URL the data came from
  • attribution — CC-BY 4.0 notice for both Open-Meteo and BOM
  • retrieved_at — UTC timestamp when we fetched
  • server_version — which wheel served the call (debugging stale uvx caches)
  • stale — true if we're serving cached data because upstream failed; comes with stale_reason

Sanity validators reject upstream values outside the plausible Australian range (temperature outside −30°C to +55°C, humidity outside 0-100%, pressure outside 850-1080 hPa). Rather than silently passing bad data to your agent, we raise an explicit validation error so the agent can degrade gracefully.

Development

git clone https://github.com/Bigred97/au-weather-mcp.git
cd au-weather-mcp
uv sync --extra dev
uv pip install -e .

# Unit tests (no network)
uv run pytest

# Live integration tests (hits Open-Meteo)
uv run pytest -m live

The SQLite cache lives at ~/.au-weather-mcp/cache.db. Current observations refresh every 15 minutes (matching Open-Meteo's update cadence), forecasts every 1 hour, historical never (a year-old day in the archive doesn't change). Delete the file to force a refresh.

Sister servers

The four packages run side-by-side in any MCP client; Claude disambiguates via the server prefix (weather:latest vs abs:latest vs rba:latest vs ato:get_data).

  • abs-mcp — Australian Bureau of Statistics: labour force, CPI, GDP, wages, housing, population
  • rba-mcp — Reserve Bank of Australia: cash rate, FX, lending rates
  • ato-mcp — Australian Taxation Office + ACNC: personal tax by postcode, company tax, charity register

Data attribution

Weather data is provided by Open-Meteo, licensed under CC BY 4.0. The underlying observations include data from the Australian Bureau of Meteorology under Open-Meteo's licensing arrangement.

Postcode resolutions (when location_resolution == "postcode") additionally use OpenStreetMap via the Nominatim service, licensed under the Open Database Licence (ODbL). The OSM attribution is automatically appended to the response's attribution field for any postcode lookup, so redistribution is licence-compliant out of the box.

If you redistribute responses, credit Open-Meteo + BOM (always) and OpenStreetMap (when postcode lookup was used).

Changelog

See CHANGELOG.md for release history.

License

MIT — Harry Vass, 2026.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured