Skip to content
Agentmart
Submit a tool

foehn

Access Swiss meteorological open data from MeteoSwiss, powered by foehn

Connector by kayhendriksen · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 45
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/kayhendriksen-foehn

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Access Swiss meteorological open data from MeteoSwiss, powered by foehn

Use cases: data-analysis

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
6 read · 0 write · 0 delete · 1 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 6 · Look things up without changing anything.

  • describe_data
  • describe_grid
  • get_inventory
  • get_parameters
  • get_stations
  • list_datasets

Not yet classified 1 · We could not tell from the name and description.

  • load_data

Network hosts it talks to 2

  • data.geo.admin.ch · found in code
  • github.com · found in code

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • describe_dataDescribe data

    Get a summary of a dataset without returning actual rows. Returns total row count, station list, date range, and column info (names, types, null counts). Use this to understand the shape and scope of data before calling load_data() — especially useful for planning queries on large historical datasets. Accepts the same filters as load_data so you can check exactly how many rows a query would return before fetching the data. **Cost note:** this still fetches the matching CSVs in full (they are not pre-bucketed by row count) and summarises them in memory — it returns no rows, but it is *not* c…

  • describe_gridDescribe grid

    Inspect a gridded dataset's structure without returning array values. The grid analog of describe_data() for the CSV path. Returns the dataset's dimensions, coordinates, data variables (each with dims, shape, dtype, units, and long_name), and key global attributes — enough to understand the grid before deciding whether to pull it down locally. Works for any gridded collection: NetCDF (climate grids, normals, scenarios, hail hazard), GRIB2 forecasts (ICON-CH1/CH2, KENDA), and HDF5/ODIM radar (CombiPrecip, hail). CSV datasets should use describe_data()/load_data(). **`match` is required for G…

  • get_inventoryGet inventory

    Get the data inventory for a dataset. Shows which parameters are available at which stations, and the time range (data_since, data_till) of available data. Args: dataset: Dataset name (e.g. "smn"). Call list_datasets() to see options.

  • get_parametersGet parameters

    Get parameter descriptions for a dataset. Returns what measurements are available (e.g. temperature, pressure, wind speed) with their short name, unit, data type, granularity, and group. Only works with CSV-backed datasets. Call this to understand what the column names in load_data() results mean. Args: dataset: Dataset name (e.g. "smn"). Call list_datasets() to see options.

  • get_stationsGet stations

    Get station metadata for a dataset. Returns station abbreviation, name, canton, altitude (m a.s.l.), LV95 coordinates, latitude, longitude, and the date measurements started in MeteoSwiss station metadata format (DD.MM.YYYY). Args: dataset: Dataset name (e.g. "smn"). Call list_datasets() to see options.

  • list_datasetsList datasets

    List all available MeteoSwiss datasets. Returns dataset name, collection ID, category, description, format, supported frequencies, and available time slices for each dataset. Args: category: Filter by category. Options: $categories. If omitted, returns all.

  • load_dataLoad data

    Load weather measurements and return rows as a list of dicts. Fetches live data from MeteoSwiss. Only works with the CSV-backed datasets named below. Binary/grid datasets (GRIB2, NetCDF, radar) are not supported — inspect those with describe_grid(). **Tip:** For historical data, always combine time filters (year, month, date_from/date_to) to avoid hitting the row limit. Use describe_data() first if you're unsure about the data shape. Args: dataset: Dataset name (e.g. "smn" for SwissMetNet). Loadable datasets: $loadable. station: Station abbreviation(s) (e.g. ["BER"] for Bern…

Compare and alternatives

    Featured in

    Signals

    Stars
    45
    Forks
    1
    Open issues
    0
    Contributors
    2
    Weekly downloads
    72
    Last commit
    Oct 15, 2026 (13 days ago)
    Last release
    Aug 28, 2026 (2 months ago)
    Last package publish
    Aug 28, 2026 (2 months ago)

    From GitHub (fetched Oct 24, 2026) and the package registry.

    Details

    Registry name
    io.github.kayhendriksen/foehn
    Version
    0.4.0
    Auth
    No auth
    Packages
    pypi foehn
    License
    MIT
    Repository
    github.com/kayhendriksen/foehn
    Website
    github.com/kayhendriksen/foehn
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql
    Cite this page

    foehn MCP server. Agent Mart. https://agentmart.dev/connectors/kayhendriksen-foehn (last updated 2026-10-24)