Skip to main content
Glama
README.md
# agro-weather-mcp

`agro-weather-mcp` is a public, open-source MCP server that gives LLMs compact,
agriculture-focused weather tools backed by the free Open-Meteo APIs. It uses
stdio only, needs no hosting, API key, or secret, and is intended for farmers,
agronomists, and agricultural software experiments.

## Install and run

With uv:

```sh
uvx --from git+https://github.com/rajshivang07/agro-weather-mcp agro-weather-mcp
```

For local development:

```sh
git clone https://github.com/rajshivang07/agro-weather-mcp
cd agro-weather-mcp
uv sync --extra dev
uv run agro-weather-mcp
```

## Who can use this and where

This server is useful anywhere an MCP-compatible assistant needs agriculture
weather context without building a custom Open-Meteo integration. It runs as a
local process over stdio, so users do not need to operate a web server, deploy
cloud infrastructure, or create an API key.

Typical users and environments include:

- Farmers who want a conversational way to check frost risk, recent water balance, or soil conditions for a field.
- Agronomists and crop advisors who need quick GDD calculations and weather summaries during field planning.
- Farm-management and precision-agriculture software teams that want reusable weather tools in an LLM workflow.
- Researchers and students prototyping crop-weather assistants without paying for a weather data service.
- Developers building local assistants in Claude Desktop, Claude Code, MCP Inspector, or another MCP-compatible client.
- Teams testing agricultural workflows before connecting them to their own field records, sensors, or farm databases.

Example workflows include:

- Geocode a farm, then inspect current and 48-hour soil conditions before discussing sowing timing.
- Calculate seasonal GDD from historical archive data and extend the range into the forecast when appropriate.
- Check the next 7 days for overnight frost exposure before recommending a field visit or crop-protection review.
- Compare precipitation with reference ET0 to identify periods that deserve closer soil-moisture monitoring.
- Use the eleven standardized tools as a weather layer inside a larger farm assistant, while keeping farm-specific decisions in the application that owns the field data.

This project is best suited to local development, personal assistants, demos,
education, research, and non-commercial prototypes that respect Open-Meteo's
free-tier terms and rate limits. It is not a replacement for a farm's weather
station, irrigation model, crop model, regulated advisory service, or local
agronomic expertise. Outputs are informational and should be reviewed before
being used in operational decisions.

### Claude Desktop

Add this entry to the Claude Desktop MCP configuration:

```json
{
  "mcpServers": {
    "agro-weather": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/rajshivang07/agro-weather-mcp", "agro-weather-mcp"]
    }
  }
}
```

### Claude Code

```sh
claude mcp add agro-weather -- uvx --from git+https://github.com/rajshivang07/agro-weather-mcp agro-weather-mcp
```

## Tools

- `geocode_location`: find candidate places and coordinates.
- `get_growing_degree_days`: calculate capped, modified-average GDD across past and forecast dates.
- `get_frost_risk`: summarize overnight minimums, threshold hours, and risk levels.
- `get_water_balance`: compare precipitation with FAO-56 reference ET0 and explain dryness.
- `get_soil_conditions`: summarize current and 48-hour soil temperature and moisture by depth.
- `get_spray_window`: find forecast windows that meet user-set wind, Delta T, temperature and rain-free limits.
- `get_heat_stress`: count forecast hours and consecutive days above a user-set temperature.
- `get_chill_hours`: accumulate chill hours or Utah chill units over a date range.
- `get_climate_anomaly`: compare a period's temperature and rainfall with the same window in baseline years.
- `get_fieldwork_window`: rate days for field access from recent and forecast rain, optionally with a topsoil moisture limit.
- `get_wetness_hours`: count humid or rainy hours within a temperature range as a leaf wetness proxy.

## Tool behavior and expected results

The tools are task-oriented interpretations of Open-Meteo data. The rule-based
notes and risk labels below are generated by this MCP server. They are not text
provided by the Open-Meteo APIs.

Every tool response includes the resolved date range, timezone, units, and
`data_source: "Open-Meteo (CC BY 4.0)"`. Coordinates are validated before a
request is made. Invalid coordinates, dates, date ranges, counts, or forecast
horizons return actionable tool errors.

### `geocode_location`

Input:

```json
{
  "name": "Davis",
  "country_code": "US",
  "count": 3
}
```

`name` is required. `country_code` is optional and must be a two-letter ISO
country code. `count` defaults to 3 and must be between 1 and 10.

The result contains candidate places with:

- `name`
- `admin_area`
- `country`
- `latitude` and `longitude` in degrees
- `elevation` in metres
- `timezone` as an IANA timezone name

This tool has no user-supplied dates, so its resolved date range is the current
date. Use the returned coordinates with the other tools.

### `get_growing_degree_days`

Input:

```json
{
  "lat": 38.54,
  "lon": -121.74,
  "start_date": "2026-04-01",
  "end_date": "2026-04-30",
  "base_temp_c": 10.0,
  "upper_cap_c": 30.0,
  "method": "modified_avg"
}
```

Dates use inclusive `YYYY-MM-DD` format. The range can be at most 366 days.
Past dates use the archive endpoint, future dates use the forecast endpoint,
and a range crossing today is split and merged automatically. Future dates are
limited by the forecast horizon of 16 days from today.

The current method is `modified_avg`. For each day, Tmin and Tmax are clamped
to the inclusive range `[base_temp_c, upper_cap_c]`, then calculated as:

```text
GDD = ((clamped Tmax + clamped Tmin) / 2) - base temperature
```

The response contains total accumulated GDD in degree-days. For ranges of 31
days or fewer it also contains daily values. Longer ranges contain weekly GDD
summaries instead. Missing daily temperatures produce a null daily value and
are excluded from the total.

### `get_frost_risk`

Input:

```json
{
  "lat": 35.68,
  "lon": 139.65,
  "days": 7,
  "threshold_c": 0.0
}
```

`days` must be between 1 and 16. `threshold_c` is in degrees Celsius. The
server requests hourly `temperature_2m` forecasts and returns each detected
night's minimum temperature and the number of hours below the threshold.

Risk is assigned using these server rules:

- `none`: zero hours below the threshold
- `low`: minimum temperature is above `threshold_c - 2 °C`
- `moderate`: minimum temperature is above `threshold_c - 5 °C`
- `high`: minimum temperature is at or below `threshold_c - 5 °C`

The result is forecast-only and covers the current date through the requested
number of forecast days in the resolved local timezone.

The tool uses 2 m air temperature from model grid data. Ground and leaf frost
can occur while the 2 m air temperature is above 0 °C, so a threshold of 2 °C
is common for cautious planning. The default stays at 0 °C; choose the
threshold that matches your own risk tolerance.

### `get_water_balance`

Input:

```json
{
  "lat": 52.52,
  "lon": 13.41,
  "start_date": "2026-06-01",
  "end_date": "2026-06-30"
}
```

Dates use inclusive `YYYY-MM-DD` format and the range can be at most 366 days.
The server combines daily precipitation and
`et0_fao_evapotranspiration`, both in millimetres, using:

```text
water balance = precipitation - reference ET0
```

The response contains total precipitation, total ET0, total balance, weekly
balance summaries, and a server-generated `dryness_note`:

The note thresholds scale with the length of the range: `0.35 mm/day`
(about 10.5 mm over 30 days) with a 5 mm floor. With threshold `T`:

| Total balance | `dryness_note` |
| --- | --- |
| at least `T` | `Likely water surplus` |
| greater than `-T` and below `T` | `Roughly balanced` |
| at or below `-T` | `Likely drying conditions; monitor soil moisture and irrigation needs` |

The response also reports the threshold used as `dryness_threshold_mm`.

The note is a simple weather-based interpretation. It is not an irrigation
recommendation and does not model crop type, soil storage, runoff, or field
conditions.

### `get_soil_conditions`

Input:

```json
{
  "lat": 42.36,
  "lon": -71.06
}
```

The server requests current and approximately 48 hours of forecast data for
the available depths:

- `0_to_7cm`
- `7_to_28cm`
- `28_to_100cm`
- `100_to_255cm`

Soil temperature is returned in degrees Celsius. Soil moisture is volumetric
water content in `m³/m³`. Each depth contains current values plus next-48-hour
minimum, maximum, and average statistics for both variables.

The response also contains this clearly labeled rough sowing guide:

```text
Many crops prefer about 8-10 °C at seed depth.
```

This is not a crop-specific threshold or agronomic recommendation. Actual
sowing decisions should use crop-specific local guidance, soil conditions, and
field observations.

### `get_spray_window`

Input:

```json
{
  "lat": 52.52,
  "lon": 13.41,
  "days": 3,
  "min_wind_kmh": 3.0,
  "max_wind_kmh": 15.0,
  "min_delta_t_c": 2.0,
  "max_delta_t_c": 8.0,
  "rain_free_hours": 3,
  "max_temp_c": 30.0
}
```

`days` must be between 1 and 7. The server forecasts hourly `temperature_2m`,
`relative_humidity_2m`, `wind_speed_10m` (requested in km/h) and
`precipitation`, and evaluates the next `days * 24` hours from the current local
hour. Delta T is air temperature minus wet-bulb temperature, where wet-bulb comes
from the Stull (2011) approximation. That approximation is defined for -20 to
50 °C and 5 to 99 % relative humidity, so hours outside that range have no Delta
T and count as unsuitable.

An hour is suitable only when all of these hold:

| Rule | Condition |
| --- | --- |
| Wind | `min_wind_kmh` <= wind <= `max_wind_kmh` |
| Delta T | `min_delta_t_c` <= Delta T <= `max_delta_t_c` |
| Temperature | temperature <= `max_temp_c` |
| Rain | no hour in the next `rain_free_hours` hourly labels has precipitation above 0.1 mm |
| Data | temperature, humidity, wind and the rain look-ahead are all available |

Open-Meteo reports precipitation for the hour before each timestamp, so the rain
check reads the labels after the evaluated hour.

Output fields: `limits`, `evaluated_hours`, `suitable_hours`, `windows` (each with
`start`, an exclusive `end`, and `hours`), `longest_window`, and
`unsuitable_hours_by_limit`. Limit names are `wind_too_low`, `wind_too_high`,
`delta_t_too_low`, `delta_t_too_high`, `delta_t_unavailable`,
`temperature_too_high`, `rain_expected` and `missing_data`. An hour that fails
several limits is counted under each. The full hourly list is not returned.

The thresholds are generic rules of thumb. The product label and local rules take
precedence, and model wind is 10 m grid data rather than wind at the nozzle.

### `get_heat_stress`

Input:

```json
{
  "lat": 30.0,
  "lon": 75.0,
  "days": 7,
  "threshold_c": 35.0
}
```

`days` must be between 1 and 16. The structure mirrors `get_frost_risk`. The
server requests hourly `temperature_2m` and returns, per local day, the maximum
temperature and the hours strictly above `threshold_c`. The result also contains
`total_hours_above_threshold` and `longest_streak_days`, the longest run of
consecutive days with at least one hour above the threshold. A day without data
ends a streak. Hourly temperatures are added as `hourly` only when `days` is 3
or fewer.

The right threshold depends on the crop, growth stage or species and must be
chosen by you. The default of 35 °C is a generic placeholder.

### `get_chill_hours`

Input:

```json
{
  "lat": 44.0,
  "lon": -121.3,
  "start_date": "2025-11-01",
  "end_date": "2026-02-28",
  "method": "below_threshold",
  "threshold_c": 7.2,
  "lower_bound_c": 0.0,
  "target_hours": 1000
}
```

Dates are inclusive and the range can be at most 366 days. Hourly `temperature_2m`
comes from the archive and the forecast, merged when the range reaches recent days.
Two methods are supported:

| Method | Rule |
| --- | --- |
| `below_threshold` | counts hours with `lower_bound_c` <= temperature <= `threshold_c`; with `lower_bound_c` set to null it counts every hour at or below the threshold |
| `utah` | Utah chill units per hour from the table below; `threshold_c` and `lower_bound_c` are ignored |

Utah weights (Richardson, Seeley and Walker, 1974, HortScience 9(4):331-332, as
commonly tabulated in degrees Celsius):

| Temperature | Chill units per hour |
| --- | --- |
| 1.4 °C or below | 0 |
| 1.5 to 2.4 °C | 0.5 |
| 2.5 to 9.1 °C | 1.0 |
| 9.2 to 12.4 °C | 0.5 |
| 12.5 to 15.9 °C | 0 |
| 16.0 to 18.0 °C | -0.5 |
| above 18.0 °C | -1.0 |

Measured temperatures fall between the tabulated tenths, so each band is applied
up to the next band's lower edge (for example 2.45 °C earns 0.5). Output fields:
`total`, `monthly` (value per month, which can be negative for Utah),
`hours_evaluated`, `hours_missing`, and `target` with `percent_of_target` when
`target_hours` is given.

Chilling requirements vary by species and cultivar and the tool carries none. The
Utah model performs poorly in warm winters.

### `get_climate_anomaly`

Input:

```json
{
  "lat": 48.85,
  "lon": 2.35,
  "start_date": "2025-06-01",
  "end_date": "2025-08-31",
  "baseline_start_year": 1991,
  "baseline_end_year": 2020
}
```

The range can be at most 366 days and must end at least 5 days before today,
because archive data lags. A later end date returns an error that names the latest
usable end date. The baseline must span at least 10 years.

For each baseline year the same window is taken: the same start month and day and
the same number of days, so totals are comparable. Feb 29 starts map to Feb 28 in
non-leap years. A window spanning New Year is labelled by the year it starts in,
and windows that would run past the final baseline year are dropped. A year with
any missing day is skipped for that variable.

For temperature (mean of the daily mean) and precipitation (total) the result
contains `target`, `baseline_mean`, `baseline_std` (sample standard deviation),
the anomaly (`anomaly_c` or `anomaly_mm`) and `percentile_rank`. The percentile is
the share of baseline years below the target, with ties counting half. Rainfall
also has `percent_of_normal`, which is null when the baseline mean is 0. The
`baseline` block reports the years used and the coordinates used.

Both the baseline and the target are requested at coordinates rounded to 0.1
degrees, so they come from the same ERA5 grid area. The baseline is cached in
memory for 24 hours per rounded location and year range. Because both sides come
from one dataset, ERA5 bias largely cancels. This is a comparison with the chosen
baseline and is not a drought index.

### `get_fieldwork_window`

Input:

```json
{
  "lat": 51.5,
  "lon": -0.1,
  "days": 7,
  "good_day_mm": 1.0,
  "good_lookback_mm": 5.0,
  "marginal_day_mm": 5.0,
  "marginal_lookback_mm": 15.0,
  "lookback_days": 3,
  "soil_moisture_max": 0.35
}
```

`days` must be between 1 and 14, `lookback_days` between 1 and 14, and
`soil_moisture_max` (optional, m³/m³) between 0 and 1. The lookback total is the
rain on the days before the day being rated, including past days. Each day is
rated:

| Rating | Rule |
| --- | --- |
| `good` | day rain <= `good_day_mm` and lookback rain <= `good_lookback_mm` |
| `marginal` | not good, but day rain <= `marginal_day_mm` and lookback rain <= `marginal_lookback_mm` |
| `poor` | anything else |
| `unknown` | rain data is missing for the day or its lookback |

When `soil_moisture_max` is set, a day whose mean forecast topsoil (0 to 7 cm)
moisture is above it drops one level (`good` to `marginal`, `marginal` to
`poor`). Output fields: `limits`, `good_days`, `longest_good_run` (`start`, `end`,
`days`, or null) and `days`, each with `rating`, `rain_mm`, `lookback_rain_mm` and
`reasons`.

This is a rain-based proxy and is not soil-texture aware, because Open-Meteo has
no soil texture data. Users with known soil should set the limits and
`soil_moisture_max` themselves.

### `get_wetness_hours`

Input:

```json
{
  "lat": 45.0,
  "lon": 9.2,
  "days": 3,
  "min_rh_pct": 90.0,
  "min_temp_c": 10.0,
  "max_temp_c": 25.0,
  "count_rain_hours": true
}
```

`days` must be between 1 and 7. An hour is wet when its temperature is within
`min_temp_c` to `max_temp_c` (inclusive) and either relative humidity is at or
above `min_rh_pct` or, when `count_rain_hours` is true, precipitation in that hour
is above 0 mm. An hour whose state cannot be decided because of missing data is
not counted and ends a run; these are reported as `hours_undetermined`.

Output fields: `criteria`, `total_wet_hours`, `longest_wet_run_hours` (over the
whole period, which can cross midnight), `hours_undetermined`, and `days` with
`wet_hours` and `longest_wet_run_hours` within each local day. `wet_hour_times`
lists the wet hours only when `days` is 3 or fewer.

This is a leaf wetness proxy only. Open-Meteo has no leaf wetness data, the
output is not a disease risk model, and no pathogen or crop presets are included.

### Choosing between similar tools

| If the question is about | Use | Not |
| --- | --- | --- |
| cold nights | `get_frost_risk` | `get_heat_stress` |
| hot hours or hot days | `get_heat_stress` | `get_frost_risk` |
| soil temperature or moisture now | `get_soil_conditions` | `get_fieldwork_window` |
| which days are workable | `get_fieldwork_window` | `get_soil_conditions` |
| rain minus ET0 over a period | `get_water_balance` | `get_wetness_hours` |
| humid or rainy hours in a temperature range | `get_wetness_hours` | `get_water_balance` |
| warm-season heat accumulation | `get_growing_degree_days` | `get_chill_hours` |
| winter chilling | `get_chill_hours` | `get_growing_degree_days` |
| a period versus normal years | `get_climate_anomaly` | `get_water_balance` |
| timing a spray | `get_spray_window` | `get_wetness_hours` |

## No crop knowledge is bundled

None of the tools knows which crop, cultivar, species or soil you are working
with. Anything crop, species or soil specific, such as a frost, heat or chill
threshold, a chilling requirement, a spray limit, rain limits for field access or
humidity limits for wetness, is a parameter with a neutral default. The defaults
are generic placeholders, not recommendations, and each tool's description says
so. Choose the values from your own agronomic guidance and local rules.

The one older exception is the short, clearly labelled `sowing_note` in
`get_soil_conditions`, which gives a rough generic soil temperature remark and is
not crop specific advice.

## Example prompts


- “Find the three closest matches for Davis, California, then calculate April GDD using a 10 C base.”
- “What is the frost risk for this location over the next seven days at 0 C?”
- “Was the last month wetter or drier than reference crop demand?”
- “What are the current and next-48-hour soil conditions at this location?”
- “Which hours in the next 3 days have wind between 3 and 15 km/h and a Delta T of 2 to 8 C, with no rain for 3 hours?”
- “How many hours above 36 C and how many consecutive hot days are forecast this week?”
- “How many chill hours between 0 and 7.2 C have accumulated since 1 November?”
- “Was last June warmer or wetter than the 1991 to 2020 normal at this location?”
- “Which days this week look workable for fieldwork if I treat more than 5 mm in 3 days as too wet?”
- “How many hours with humidity of 90 percent or more between 10 and 25 C are forecast over 3 days?”

## Scope and guardrails

This server answers weather questions for agriculture. It does not answer
everything a farm assistant might be asked, and the model using it should say so
instead of stretching a tool to fit. Out of scope, with no tool to call:

- Anything unrelated to farm weather: general chat, coding, news, finance, health.
- Agronomic decisions: product doses, crop or cultivar choice, disease diagnosis,
  yield prediction, irrigation volumes, and legal or label compliance.
- Data this server does not have: soil texture, satellite imagery, sensors or leaf
  wetness measurements, market prices, pest counts, hail or lightning alerts, and
  anything before 1940 or more than 16 days ahead.

Built-in guardrails:

- **Validation before any request:** invalid coordinates, dates, ranges and day
  counts return an error and no Open-Meteo request is made. Coordinates are never
  corrected silently.
- **No silent all-clear:** NaN or infinite thresholds are rejected, because they
  would turn every comparison false and report "no frost" or "no heat". An empty
  upstream response is an error rather than a zero result, and missing hours are
  counted (`hours_missing`, `hours_undetermined`, `missing_data`, `unknown`).
- **Caveats in the response:** `get_spray_window`, `get_fieldwork_window` and
  `get_wetness_hours` return a `note` saying that the limits are generic, that the
  rating is a proxy, and that the product label and local rules take precedence.
- **No crop knowledge:** a test fails if a tool schema, description or source file
  names a specific crop.
- **External text is data:** place names from the geocoder are shortened to 100
  characters and flattened to one line before they are returned.
- **Rate limits:** repeated identical requests are served from a short in-memory
  cache. Do not use this server for bulk or commercial scraping of Open-Meteo.

`docs/EVALS.md` includes prompts where the correct behaviour is to call no tool.

## Caution: what is not fully verified

Please read this before relying on the tools. These points were not verified or
rest on assumptions, as of version 0.2.0:

- **Test data:** the automated tests use fixtures written by the authors, not
  recorded Open-Meteo responses. A live smoke test per tool confirms that real
  requests succeed and return the expected fields, but it does not check the
  numbers against an independent source.
- **Utah chill units:** the temperature bands and weights come from published
  software implementations that cite Richardson et al. (1974). The original paper
  was not consulted. Temperatures between the tabulated tenths are assigned to the
  band below the next band's lower edge, so 1.45 °C counts as 0. The Utah model
  also performs poorly in warm winters.
- **Wet-bulb and Delta T:** the Stull (2011) approximation is stated to be accurate
  within about -1 to +0.65 °C, only for -20 to 50 °C and 5 to 99 % relative
  humidity, and it assumes standard sea-level pressure. Results at high elevation
  are less accurate. The formula was checked against Stull's published example and
  an independent psychrometric calculation, not against the original paper's text.
- **Archive lag:** the server assumes archive data is final about 5 days behind
  today and takes more recent dates from the forecast. The real lag can differ, and
  recent archive values can be revised.
- **Forecast history:** the hourly helper reaches back at most 92 days through
  Open-Meteo's `past_days` parameter, the documented limit.
- **Daylight saving time:** hourly timestamps are treated as a regular grid of local
  labels. Behaviour around clock changes was not tested.
- **Rate limits and large requests:** behaviour under repeated use of the free tier
  was not tested. `get_climate_anomaly` downloads a 30-year daily baseline (about
  11,000 rows) once per rounded location, then caches it for 24 hours in memory.
- **Model data, not measurements:** all values are gridded model or reanalysis data,
  including 10 m wind, 2 m air temperature and topsoil moisture. They can differ
  from conditions in your field, at the nozzle or at canopy height.
- **Proxies and rules of thumb:** `get_fieldwork_window` is a rain-based proxy that
  is not soil-texture aware, `get_wetness_hours` is a leaf wetness proxy and not a
  disease model, and the spray limits are generic rules of thumb. The product label
  and local rules take precedence.
- **Defaults are placeholders:** no default threshold is crop, cultivar, species or
  soil specific advice. See "No crop knowledge is bundled".

## Data and limits

Data comes from Open-Meteo, attributed as **Open-Meteo (CC BY 4.0)**. The archive
tool uses ERA5-style historical data and forecast requests use the Open-Meteo
forecast API. Open-Meteo's free tier is for non-commercial use and has rate
limits. Check the Open-Meteo terms and documentation for current limits before
deploying repeated or commercial workloads.

Outputs are informational and are not agronomic advice. Weather, soil, crop,
and management decisions require local expertise and appropriate observations.

## Testing with MCP Inspector

Run the server through the MCP Inspector with the project command configured as
`uv run agro-weather-mcp` and transport set to stdio. The Inspector can list the
eleven tools and invoke them with JSON arguments without needing a hosted endpoint.

## Development

```sh
uv sync --extra dev
uv run ruff check .
uv run ruff format --check .
uv run pytest
```

Live smoke tests are excluded by default. Set `RUN_LIVE=1` to run them.

TDQS

A3.9/5.0

Scored across 5 tools

Disambiguation5/5

Each tool covers a clearly distinct agronomic concept: place lookup, growing degree days, frost risk, water balance, and soil conditions. There is virtually no overlap—the shared lat/lon/date signature is a consistent input convention, not a source of confusion, and the descriptions make each tool's specific output obvious.

Naming Consistency4/5

All names follow a clean verb_noun snake_case pattern (geocode_location, get_growing_degree_days, get_frost_risk, get_water_balance, get_soil_conditions). The only minor deviation is 'geocode_location' using a domain-specific verb 'geocode' instead of the otherwise dominant 'get_' prefix, but it is still readable and predictable.

Tool Count5/5

Five tools is a tight, well-scoped set for a focused agro-weather service, with each tool covering a distinct analytical need. Nothing feels redundant or missing at the count level; it sits comfortably in the ideal 3-15 range.

Completeness4/5

The surface covers geocoding plus the core agronomic analytics (GDD, frost, water balance, soil), giving a coherent lifecycle for planning decisions. However, there is no general-purpose raw weather forecast or daily temperature/precipitation retrieval tool, which agents might reasonably expect from an agro-weather server as a fallback.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues