meteoswiss-mcp
Meteoswiss-mcp exposes six read-only MCP tools for Swiss weather, climate, and official warning data.
List embedded SwissMetNet stations, optionally filtered by canton (
meteo_stations).Fetch current 10-minute observations for a station: temperature, precipitation, sunshine, wind, humidity, pressure (
meteo_current).Get 1β16 day forecasts for a place or coordinates, with optional hourly values, using MeteoSwiss ICON/Open-Meteo (
meteo_forecast).Check outdoor school-event suitability with a π’/π‘/π΄ traffic light for coming days or a specific date (
meteo_school_check).Retrieve monthly 1991β2020 climate normals (temperature, precipitation, sunshine) for embedded stations (
meteo_climate_normals).Fetch active official MeteoSwiss weather warnings nationwide, by canton, or by PLZ, with warning levels and links (
meteo_warnings).
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., "@meteoswiss-mcp What's the current weather in Zurich?"
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.
π¦οΈ meteoswiss-mcp
MCP server for Swiss weather and climate data from MeteoSwiss.
Connects AI models to the SwissMetNet measurement network (160+ stations, 10-minute interval), MeteoSwiss ICON-CH1/CH2-EPS forecasts and climate normals 1991β2020. Part of the swiss-public-data-mcp portfolio.
π©πͺ Deutsche Version
Demo query (anchor example)
How suitable is next Wednesday for the sports day at Leutschenbach school?β meteo_school_check(location="ZΓΌrich Oerlikon", activity="Sporttag") returns a π’/π‘/π΄ traffic light for each day of the coming week β straight from the MeteoSwiss ICON model.
Combined with swiss-environment-mcp:
How were air quality and weather at Leutschenbach school yesterday?β meteo_current(station='REH') + env_nabel_current(station='ZUE') = a complete environmental picture.
β More use cases by audience β
Related MCP server: MeteoSwiss MCP Server
Tools (6)
Tool | Description | Data source |
| List SwissMetNet stations (filterable by canton) | Embedded |
| Current 10-min observations for a station | BGDI STAC API |
| 1β16 day forecast for a place or coordinates | Open-Meteo / MeteoSwiss ICON |
| π’/π‘/π΄ traffic light for outdoor school events | Open-Meteo / MeteoSwiss ICON |
| Monthly climate normals 1991β2020 | Embedded (KLO, SMA, BER, LUG, GVE) |
| Active official weather warnings (storm, thunderstorm, heat, forest fire, β¦) β nationwide, by canton, or by PLZ | MeteoSwiss App-API + opendata.swiss |
Tool annotations (MCP hints)
All tools carry explicit MCP annotations β relevant for the client approval UI and for the LLM's safety decisions.
Tool |
|
|
|
|
| β | β | β | β (curated list) |
| β | β | β (live data) | β (upstream STAC) |
| β | β | β (live data) | β (upstream Open-Meteo) |
| β | β | β (live data) | β (geocoding + forecast) |
| β | β | β | β (embedded normals) |
| β | β | β (live data) | β (MeteoSwiss App-API) |
Read rules: all 6 tools are readOnly + non-destructive β the server fundamentally cannot write or delete anything. idempotentHint=False marks tools that return different values depending on when they are called.
MCP protocol version
Aspect | Value |
Tested spec versions |
|
MCP SDK version | see |
Update policy | Dependabot watches |
β Full roadmap & update strategy: docs/roadmap.md
Quick start
Claude Desktop
{
"mcpServers": {
"meteoswiss": {
"command": "uvx",
"args": ["meteoswiss-mcp"]
}
}
}Claude Desktop (local development)
{
"mcpServers": {
"meteoswiss": {
"command": "uv",
"args": ["run", "--directory", "/path/to/meteoswiss-mcp", "meteoswiss-mcp"]
}
}
}Cloud / Render.com (Streamable HTTP)
Configuration via ENV variables (the CLI flags --http / --port N still work as an override):
Variable | Default | Meaning |
|
|
|
|
| Bind address β never change locally |
|
| Port |
| unset | Must be set to |
|
|
|
| unset | Comma-separated list of allowed origins for CORS. Empty = CORS disabled (same-origin only). |
| unset | If set: every request except |
|
|
|
| unset | If set + |
|
| Service name in the OTel resources |
|
|
|
|
| TTL in seconds for STAC SMN observations (default 5 min) |
|
| TTL for ICON forecasts (default 10 min) |
|
| TTL for geocoding lookups (default 1 h) |
|
| TTL for the opendata.swiss catalogue (default 1 h) |
|
| TTL for warnings (MeteoSwiss App-API / structured override; default 5 min) |
| unset | Path to a JSON file with additional climate normals β see |
| unset | Override for the default MeteoSwiss App-API source: URL of a structured MeteoSwiss warnings API (e.g. the future OGD warnings REST endpoint). The host must be on the egress allow-list. Schema-tolerant (GeoJSON |
| unset | URL template for runtime lookup of climate normals (for stations without embedded or JSON values). Tokens: |
# Local test (safe, loopback only)
MCP_TRANSPORT=streamable-http meteoswiss-mcp
# Container / Render
MCP_TRANSPORT=streamable-http MCP_HOST=0.0.0.0 MCP_ALLOW_ANY_HOST=1 meteoswiss-mcpDocker / Render
The repo includes a production-ready multi-stage Dockerfile (non-root user, HEALTHCHECK) and a render.yaml blueprint:
# Build + test locally
docker build -t meteoswiss-mcp .
docker run --rm -p 8000:8000 meteoswiss-mcp
curl http://127.0.0.1:8000/health # β {"status":"ok","service":"meteoswiss-mcp"}On Render: "New β Blueprint" β select the repo. Defaults (plan starter, Frankfurt, single instance) are set in render.yaml.
Important: numInstances: 1 is set deliberately β sticky-session routing for multi-replica (audit SCALE-002/003) is not yet implemented.
Structured logging
All tool invocations, upstream failures and egress blocks are emitted as JSON events on stderr (stdio-transport safe). Example:
{"tool": "meteo_forecast", "days": 7, "has_coords": false, "event": "tool_invoked", "level": "info", "timestamp": "2026-05-20T07:00:00Z"}
{"tool": "meteo_forecast", "endpoint": "geocoding", "error_type": "HTTPStatusError", "event": "upstream_failed", "level": "warning", "timestamp": "..."}
{"url": "https://evil.example.com/", "method": "GET", "reason": "host not in allow-list", "event": "egress_blocked", "level": "warning", "timestamp": "..."}HTTP-mode security
MCP_HOSTdeliberately defaults to127.0.0.1so that--httpon a dev laptop is not accidentally exposed to the local subnet (audit finding SEC-016).All outgoing HTTP calls (including redirect follows) are validated against an allow-list:
data.geo.admin.ch,api.open-meteo.com,geocoding-api.open-meteo.com,opendata.swiss. Other hosts and IP literals (in particular169.254.169.254, RFC1918) are rejected withEgressBlocked(SEC-004 / SEC-021).CORS: disabled by default (same-origin only). Browser clients (e.g. claude.ai web) need
MCP_ALLOWED_ORIGINS=<csv>β theMcp-Session-Idheader is then automatically inAccess-Control-Expose-Headers(SDK-004).API-key auth: disabled by default. In a production HTTP setup, always set
MCP_API_KEY=<random>β requests without a validX-API-KeyorAuthorization: Bearer β¦are rejected with 401 (SEC-009 / SEC-013)./healthstays open for container health probes.
Example: production HTTP stack
# 32 bytes of randomness as the auth key
export MCP_API_KEY=$(python -c "import secrets; print(secrets.token_urlsafe(32))")
MCP_TRANSPORT=streamable-http \
MCP_HOST=0.0.0.0 \
MCP_ALLOW_ANY_HOST=1 \
MCP_ALLOWED_ORIGINS=https://app.example.com \
MCP_API_KEY="$MCP_API_KEY" \
meteoswiss-mcpExample queries
School planning
Which days next week are suitable for a sports day in ZΓΌrich?
β meteo_school_check(location="ZΓΌrich", activity="Sporttag")
What will the weather be at Leutschenbach school on Friday?
β meteo_forecast(location="ZΓΌrich Oerlikon", days=5)
Show me current readings from the nearest MeteoSwiss station to ZΓΌrich-Schwamendingen.
β meteo_current(station="REH")Climate comparison
How much rain normally falls in June in ZΓΌrich?
β meteo_climate_normals(station="KLO")
Is Lugano really much sunnier than ZΓΌrich? Show me the annual values.
β meteo_climate_normals(station="LUG") + meteo_climate_normals(station="SMA")Infrastructure & environment
Are there currently any weather warnings for the canton of ZΓΌrich?
β meteo_warnings(canton="ZH")
Show me a 10-day forecast for the HeerenschΓΌrli sports facility with hourly values.
β meteo_forecast(location="Sportanlage HeerenschΓΌrli ZΓΌrich", days=10, hourly=True)Architecture
Claude Desktop / AI agent
β
β MCP (stdio / Streamable HTTP)
βΌ
meteoswiss-mcp (MCPServer)
β
βββ meteo_stations ββββββββββββββββ [embedded: ~20 SMN stations]
β
βββ meteo_current βββββββββββββββββ BGDI STAC API
β data.geo.admin.ch/api/stac/v1
β Collection: ch.meteoschweiz.ogd-smn
β
βββ meteo_forecast ββββββββββββββββ Open-Meteo
βββ meteo_school_check ββββββββββββ api.open-meteo.com/v1/meteoswiss
β (MeteoSwiss ICON-CH1/CH2-EPS, 1β2 km)
β
βββ meteo_climate_normals βββββββββ [embedded: normals 1991β2020]
β
βββ meteo_warnings ββββββββββββββββ app-prod-ws.meteoswiss-app.ch
(MeteoSwiss App-API) + opendata.swissData sources
Source | URL | License |
BGDI STAC API (MeteoSwiss OGD) |
| CC BY 4.0 |
Open-Meteo (MeteoSwiss ICON) |
| CC BY 4.0 |
Open-Meteo Geocoding |
| CC BY 4.0 |
opendata.swiss CKAN |
| CC BY 4.0 |
MeteoSwiss App-API (warnings) |
| CC BY 4.0 |
Safety & limits
Aspect | Details |
Access | Read-only ( |
Personal data | No personal data β all sources are aggregated, publicly available open data |
Rate limits | Built-in per-query caps: max 50 results per API call, 30 s timeout |
Authentication | No API keys required β all data sources are publicly accessible |
Licenses | All data under CC BY 4.0 (MeteoSwiss Open Government Data) |
Terms of Service | Subject to the ToS of the respective data sources: MeteoSwiss OGD, Open-Meteo, opendata.swiss |
Known limitations
ID | Tool | Description |
BUG-01 |
| STAC asset structure can vary per station; fallback to a direct link is implemented |
LIM-01 |
| Only 5 stations embedded (KLO, SMA, BER, LUG, GVE); the rest via an opendata.swiss link |
LIM-02 |
| Live warnings come from the MeteoSwiss App-API ( |
LIM-03 |
| Shows 10-min values in UTC; no automatic conversion to local time |
Responsibility matrix β snow & precipitation (delineation vs. swiss-environment-mcp)
To avoid duplicating snow and precipitation data across the portfolio,
responsibilities are split as follows. meteoswiss-mcp owns atmospheric
precipitation and weather; swiss-environment-mcp (SLF domain) owns snow on the
ground and avalanche danger.
Data | meteoswiss-mcp (MeteoSwiss) | swiss-environment-mcp (BAFU / SLF) |
Precipitation amount (mm): measurement network, forecast, climate normals | β
| β |
Snowfall as a current weather condition | β
| β |
Weather warnings (storm, thunderstorm, heat) | β
| β |
Snow depth on the ground ( | β | β SLF IMIS / study-plot ΒΉ |
Fresh snow 24 h ( | β | β SLF ΒΉ |
Avalanche danger level | β | β SLF avalanche bulletin ΒΉ |
Natural-hazard warnings (flood, avalanche, wildfire) | β | β
|
Rule: atmospheric precipitation (rain/snowfall as mm) plus weather,
forecast, warnings and climate normals belong to meteoswiss-mcp; snow on the
ground and avalanche danger belong to swiss-environment-mcp (SLF). The SLF
IMIS precipitation sensor is used there only as context for the snowpack and is
never exposed as a precipitation tool, so it does not duplicate MeteoSwiss.
ΒΉ SLF/snow tools in swiss-environment-mcp are in preparation (Phase-1 live-probe
completed 2026-07-19, see that repo's docs/probe-slf.md); the demarcation is
fixed now so the two servers do not collide once implemented.
Portfolio synergies
meteoswiss-mcp
β
βββ swiss-environment-mcp Combine weather + air quality (NABEL)
β "How were weather AND air at Leutschenbach school?"
β
βββ zurich-opendata-mcp School locations β weather forecast
"Which schools in ZΓΌrich have sports-day weather?"MCP Protocol Version
This server speaks two protocol eras over the same endpoint. The client's first request on a connection decides which one applies; a later claim from the other era is refused.
Era | Revision | Who reaches it |
|
| What today's clients speak. The server answers with the revision asked for, or with the |
Per-request envelope |
| A request carrying the |
Both revisions are pinned in
tests/test_protocol_version.py and asserted
against the installed SDK, so a Dependabot bump of mcp cannot move either one
silently. It is also measured on the wire:
tests/test_spec_2026.py sends real requests of
both eras through the same ASGI stack main() hands to uvicorn β a
2026-07-28 tool call with no handshake and no session, and an initialize
that is capped at 2025-11-25.
No deprecated capability. 2026-07-28 deprecates logging, sampling and
roots (SEP-2577). The server calls none of them: in-flight status goes out as
notifications/progress (reaching any client that sends a progressToken, in
both eras), and failures are stated in the tool result itself. A test keeps
the source free of ctx.info/ctx.warning and friends.
Note that the SDK's LATEST_PROTOCOL_VERSION is an alias for the modern
era, not for the handshake era β pinning against it alone would leave the era
that current clients actually negotiate free to drift.
Update policy. When the gate fails, do not edit the constant blindly: read
the spec changelog between the two revisions, verify the server still behaves,
then move the constant, this section, README.de.md and
CHANGELOG.md together.
Testing
# Unit tests (no network)
PYTHONPATH=src pytest tests/ -m "not live" -v
# Live tests (real APIs) β also run daily at 05:17 UTC via
# .github/workflows/live-tests.yml, so a format change upstream
# surfaces even though the unit tests stay green.
PYTHONPATH=src pytest tests/ -m live -v
# Linting β install the local gates once with `pre-commit install`
# to run these (and the CI guards) before every commit.
ruff check src/ tests/ scripts/
ruff format --check src/ tests/ scripts/Development
git clone https://github.com/malkreide/meteoswiss-mcp
cd meteoswiss-mcp
pip install -e ".[dev]"MCP Inspector (local test)
PYTHONPATH=src npx @modelcontextprotocol/inspector python -m meteoswiss_mcp.serverContributing
See the contributing guidelines (Deutsch).
Security
See the security policy (Deutsch) for the security posture and how to report a vulnerability.
License
MIT License β see LICENSE.
Source data: MeteoSwiss Open Government Data (CC BY 4.0). When using the data, cite: Source: MeteoSwiss.
Author
Hayal Oezkan Β· github.com/malkreide
Related servers
Installation
Run via uv's uvx β no clone or manual install needed. Add to your MCP client config (mcpServers for Claude Desktop, Cursor and Windsurf; use a top-level servers key for VS Code in .vscode/mcp.json):
{
"mcpServers": {
"meteoswiss-mcp": {
"command": "uvx",
"args": [
"meteoswiss-mcp"
]
}
}
}Available Tools
6 toolsmeteo_climate_normalsARead-onlyIdempotent
<use_case> Monatliche 30-Jahres-Klimanormwerte (Temperatur β , Niederschlag, Sonnenstunden) fΓΌr eine MeteoSwiss-Station. Referenz fΓΌr Β«typisches WetterΒ» β Schuljahresplanung, Veranstaltungs-Budgetierung, Vergleich mit aktuellen Messwerten. </use_case>
<important_notes>
Periode: 1991β2020 (WMO-Standard)
Eingebettete Normwerte verfΓΌgbar: KLO, SMA, BER, LUG, GVE
FΓΌr andere Stationen: Tool gibt Liste verfΓΌgbarer Codes + opendata.swiss-Link
Statische Daten β Tool ist idempotent, kein Netzwerk-Roundtrip </important_notes>
Args: params (ClimateNormalsInput): - station: SMN-KΓΌrzel (z.B. 'KLO', 'SMA', 'BER') - response_format: 'markdown' oder 'json'
Returns: str: Monatliche Klimanormwerte-Tabelle 1991β2020.
Inputs: params (required). Returns: result
meteo_currentARead-only
<use_case> Aktuelle 10-Minuten-Wettermesswerte einer SwissMetNet-Station abrufen (Temperatur, Niederschlag, Sonnenschein, Wind, Feuchte, Druck). </use_case>
<important_notes>
GranularitΓ€t: 10-Minuten-Werte, letzte ~6 Beobachtungen
Quelle: BGDI STAC API (data.geo.admin.ch)
Live-Daten β Tool ist NICHT idempotent
Bei Upstream-Ausfall: Fallback mit Direktlinks statt Hard-Fail </important_notes>
Args: params (CurrentInput): - station: SMN-KΓΌrzel, z.B. 'KLO', 'SMA', 'REH', 'BER' - response_format: 'markdown' oder 'json'
Returns: str: Aktuelle Messwerte mit Zeitstempel, oder Fallback mit Direktlinks.
Inputs: params (required). Returns: result
meteo_forecastARead-only
<use_case> 1-16 Tage Wetterprognose fΓΌr einen Ortsnamen oder Koordinaten β basierend auf dem MeteoSwiss-ICON-Modell (1-2 km AuflΓΆsung). Liefert Tageswerte (Temperatur Min/Max, Niederschlag, Wind, UV, Sonnenstunden, WMO-Code) und optional Stundenwerte. </use_case>
<important_notes>
Modell: MeteoSwiss ICON-CH1/CH2 via Open-Meteo fΓΌr Tag 1-5; darΓΌber hinaus sowie fΓΌr den UV-Index Open-Meteo best_match, weil ICON nur 5 Tage weit reicht und keinen UV-Index fΓΌhrt. Welcher Teil woher stammt, steht in jeder Antwort (Markdown-Fussnote bzw. JSON-Feld
modell/modell_details)location wird geokodiert (Fuzzy-Fallback bei Misserfolg); lat/lon ΓΌberschreibt location und spart einen HTTP-Roundtrip
StΓΌndliche Daten fΓΌllen die ersten 48 Stunden, nicht den vollen Range
Bei Upstream-Ausfall: Direktlinks statt Hard-Fail </important_notes>
Args: params (ForecastInput): - location: Ortsname (geokodiert) ODER lat/lon direkt - days: Prognosetage (1β16, Standard: 7) - hourly: True fΓΌr Stundenwerte - response_format: 'markdown' oder 'json'
Returns: str: Tages- (und optional Stunden-)Prognose mit Wettercode und Planung.
Inputs: params (required). Returns: result
meteo_school_checkARead-only
<use_case> Aggregiert Geocoding + 7-Tage-Forecast + Schwellenwert-Check zu einer Ampel-Bewertung (π’/π‘/π΄) fΓΌr Schulveranstaltungen im Freien. Ein Tool-Call ersetzt die Kombi meteo_forecast + manuelle Bewertung. </use_case>
<important_notes> Schwellenwerte:
Temperatur: 5β33 Β°C (sonst zu kalt / zu heiss)
Niederschlag: < 1.5 mm/Tag
Wind: < 50 km/h
UV-Index β₯ 6: Warnung (Sonnenschutz) Quelle: SUVA / BAG / MeteoSchweiz-Warnklassen. Bei date-Parameter: nur dieser eine Tag wird zurΓΌckgegeben. </important_notes>
Args: params (SchoolCheckInput): - location: Ort (geokodiert), z.B. 'ZΓΌrich Oerlikon' - date: Optional β spezifischer Tag (YYYY-MM-DD) - activity: Art der AktivitΓ€t ('Sporttag', 'Schulreise', etc.)
Returns: str: Ampel-Bewertung fΓΌr die nΓ€chsten 7 Tage (oder Einzeltag).
Inputs: params (required). Returns: result
meteo_stationsARead-onlyIdempotent
<use_case> Liefert eine Γbersicht der SwissMetNet (SMN)-Messstationen, die in diesem Server eingebettet sind. NΓΌtzlich, um StationskΓΌrzel fΓΌr meteo_current oder meteo_climate_normals zu finden. </use_case>
<important_notes>
Kuratierte Auswahl (~20 Stationen) mit Schul-/Stadtplanungs-Fokus
Datenquelle: MeteoSwiss SMN-Katalog (160+ Stationen total)
Lizenz: CC BY 4.0 β Quelle: MeteoSchweiz </important_notes>
Schul-Tipp: Station REH (ZΓΌrich/Affoltern) ist die nΓ€chste SMN-Station zum Schulhaus Leutschenbach.
Args: params (StationsInput): - canton: KantonskΓΌrzel (z.B. 'ZH') β leer = alle - response_format: 'markdown' oder 'json'
Returns: str: Stationsliste mit KΓΌrzel, Name, Kanton, Koordinaten und HΓΆhe.
Inputs: params (required). Returns: result
meteo_warningsARead-only
<use_case> Aktive amtliche MeteoSwiss-Wetterwarnungen (Gewitter, Sturm, Starkregen, Schnee, Hitze, Frost, Waldbrand, ...) live abrufen β landesweit, pro Kanton oder ortsgenau via PLZ. ErgΓ€nzt um Warnkarte, MeteoAlarm und OGD-Katalog. </use_case>
<important_notes>
Live-Quelle ist das ΓΆffentliche MeteoSwiss-App-Backend (
app-prod-ws.meteoswiss-app.ch/v1/plzDetail); es gibt keinen landesweiten Sammel-Endpoint, daher wird ohneplz/cantonje eine Kantonshauptort-PLZ pro Kanton abgefragt und aggregiert. FΓΌr ortsgenaue Warnungenplzsetzen.Warnstufen-Skala: 1=Keine/gering, 2=Gering, 3=MΓ€ssig, 4=Stark, 5=Sehr stark.
Bei aktiven Warnungen Stufe 4+: Aussenveranstaltungen verschieben.
MCP_WARNINGS_API_URLΓΌberschreibt die App-Quelle (Vorbereitung auf die kΓΌnftige offizielle OGD-Warnings-REST-API). </important_notes>
Args: params (WarningsInput): - canton: KantonskΓΌrzel zum Filtern (z.B. 'ZH') - plz: 4-stellige PLZ fΓΌr ortsgenaue Warnungen (z.B. '8001') - language: 'de' | 'fr' | 'it' | 'en' (Sprache der Warntexte) - response_format: 'markdown' oder 'json'
Returns: str: Aktive Warnungen + Warnkarte/MeteoAlarm-Links.
Inputs: params (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 6 tools
Each tool targets a distinct meteorological resource: station metadata, current obs, forecasts, climate normals, warnings, and an aggregated school-specific check. There is no overlap or ambiguity between them.
All six tools follow a consistent 'meteo_' prefix plus a clear noun or composite noun (stations, current, forecast, school_check, climate_normals, warnings). The pattern is uniform and predictable.
Six tools provide a well-scoped coverage of weather data and domain-specific analysis for an MCP server focused on Swiss meteorology. No tool feels redundant and none are missing to justify a larger set.
The server covers the core weather workflows: station lookup, current conditions, forecasts, climatological normals, and warnings. A minor gap is the lack of historical actual observations (e.g., past dates), but the provided climate normals and current/forecast data cover typical planning needs.
Maintenance
Related MCP Connectors
Swiss weather data for AI assistants β forecasts, measurements, stations, pollen.
Swiss weather and federal geodata from MeteoSwiss and swisstopo on data.geo.admin.ch β findβ¦
Global weather via Open-Meteo: forecast, historical, marine, air quality, geocoding, elevation.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
Related MCP Servers
- AlicenseDqualityFmaintenanceProvides Swiss weather forecast data, allowing users to search for Swiss locations and get detailed hourly and daily weather forecasts.22MIT
- AlicenseNot gradedqualityBmaintenanceProvides access to official MeteoSwiss weather data, including regional reports, daily forecasts, and website search functionality across multiple languages. It enables AI assistants to retrieve real-time weather information and documentation from MeteoSwiss using the Model Context Protocol.4Creative Commons Zero v1.0 Universal
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to access live weather data from Environment and Climate Change Canada via the GeoMet API.128 npmMIT
- AlicenseAqualityAmaintenanceConnects AI assistants to Swiss environmental data from BAFU, including air quality, hydrology, natural hazards, and open datasets, with no API keys required.2153 PyPI1MIT