# Meltema Weather (remote · meltema.com)

Multi-model weather forecasts: point series, model scoreboard, and gridded fields. No auth.

- Trust score: 69/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `meltema.com`: 69/100 (this document), [markdown](https://verifymcp.io/servers/com-meltema-weather/meltema.md), [page](https://verifymcp.io/servers/com-meltema-weather/meltema)

## Channel facts

- Endpoint: `https://meltema.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1451 tokens (~241/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-meltema-weather https://meltema.com/mcp
```

### Codex

```toml
[mcp_servers.com-meltema-weather]
url = "https://meltema.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-meltema-weather": {
      "type": "remote",
      "url": "https://meltema.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-meltema-weather --url https://meltema.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-meltema-weather:
    url: "https://meltema.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-meltema-weather": {
      "type": "http",
      "url": "https://meltema.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 68, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 67, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 65)

First indexed and scored.

## MCP tools (5)

### `list_sources` (~42 tokens)

List forecast sources

Every public forecast source with live-data status, servable variables, cadence and licensing attribution. This is the live enum of `source_id` accepted by the other tools.

Output parameters:

- `result` (array)

### `list_runs` (~58 tokens)

List stored runs

Stored run init times for a source, newest first (UTC ISO 8601). Pass one to pin a tool to that run.

Input parameters:

- `source_id` (string, required): A `source_id` from list_sources, e.g. `gfs`.

Output parameters:

- `result` (array)

### `point_forecast` (~482 tokens)

Point forecast

Full forecast horizon of one model at a single point (bilinear grid sample). source_id is OPTIONAL: omit it and a sensible live source is chosen (prefers gfs, then ifs_open) and returned as `source_id`. Omit init_time for the latest run; omit variables for all stored variables plus derived wind_speed. Canonical variable ids: t2m = 2 m air temperature (K), u10 = 10 m U wind component (m/s), v10 = 10 m V wind component (m/s), wind_speed = 10 m wind speed, derived hypot(u10, v10) (m/s), tp = total precipitation over the step (kg m-2, mm-equivalent), tcc = total cloud cover (fraction 0-1), ssrd = surface downward shortwave radiation (W m-2), msl = mean sea level pressure (Pa) (availability varies by source — see GET /v1/sources). Common aliases are accepted case-insensitively and normalized to these ids: temperature/temperature_2m/temp -> t2m, wind/windspeed/wind_speed_10m -> wind_speed, u10m/v10m -> u10/v10, precip/precipitation/rain -> tp, cloud/clouds/cloud_cover -> tcc, solar/radiation/shortwave -> ssrd, pressure/mslp/sea_level_pressure -> msl. The output series always carries the canonical id.

Input parameters:

- `init_time`: Run init (UTC ISO 8601); omit for the latest run.
- `lat` (number, required): Latitude, degrees north.
- `lon` (number, required): Longitude, degrees east (normalized to [-180,180)).
- `source_id`: A `source_id` from list_sources. OPTIONAL — omit to use a sensible live default (prefers gfs, then ifs_open); the chosen source is echoed as the result's `source_id`.
- `variables`: Comma-separated variable ids (t2m, u10, v10, wind_speed, tp, tcc, ssrd, msl); omit for all + wind_speed. Common aliases like temperature_2m/windspeed/precipitation/cloud/solar/pressure are accepted (…

Output parameters:

- `init_time` (string): Run init time (UTC ISO 8601) actually sampled.
- `lat` (number)
- `lon` (number): Longitude normalized into [-180, 180).
- `series` (array)
- `source_id` (string)

### `compare_models` (~400 tokens)

Compare models at a point (scoreboard)

Sample one variable at a point across many models and summarize per-time cross-model spread (min/max/mean/spread). Sources default to every live source carrying the variable; pass a comma-separated `sources` to pin the set. Canonical variable ids: t2m = 2 m air temperature (K), u10 = 10 m U wind component (m/s), v10 = 10 m V wind component (m/s), wind_speed = 10 m wind speed, derived hypot(u10, v10) (m/s), tp = total precipitation over the step (kg m-2, mm-equivalent), tcc = total cloud cover (fraction 0-1), ssrd = surface downward shortwave radiation (W m-2), msl = mean sea level pressure (Pa) (availability varies by source — see GET /v1/sources). Common aliases are accepted case-insensitively and normalized to these ids: temperature/temperature_2m/temp -> t2m, wind/windspeed/wind_speed_10m -> wind_speed, u10m/v10m -> u10/v10, precip/precipitation/rain -> tp, cloud/clouds/cloud_cover -> tcc, solar/radiation/shortwave -> ssrd, pressure/mslp/sea_level_pressure -> msl. The output series always carries the canonical id.

Input parameters:

- `init_time`: Run init (UTC ISO 8601); omit for each source's latest run.
- `lat` (number, required): Latitude, degrees north.
- `lon` (number, required): Longitude, degrees east.
- `sources`: Comma-separated `source_id`s; omit to use every live source with the variable.
- `variable` (string, required): A single variable id, e.g. t2m, tp, tcc, ssrd (or an alias like temperature_2m/precipitation — normalized to the canonical id).

Output parameters:

- `consensus` (array): Per-valid_time cross-model spread, ascending.
- `lat` (number)
- `lon` (number)
- `missing` (array): Requested/eligible sources with no data for this variable.
- `models` (array)
- `variable` (string)

### `describe_grid` (~113 tokens)

Describe a gridded field

Geometry (grid spec + available leads + units) of a gridded field, plus the exact /v1/grid URL and the recipe to decode the raw uint16 bytes. Omit init_time for the latest run.

Input parameters:

- `init_time`: Run init (UTC ISO 8601); omit for the latest run.
- `source_id` (string, required): A `source_id` from list_sources.
- `variable` (string): Variable id, e.g. `t2m` or composite `wind10m`.

Output parameters:

- `decode` (string): How to turn the uint16 body into physical values.
- `fetch_url` (string): GET this for the raw uint16 field (add ?lead_hours=&stride=).
- `grid`
- `init_time` (string)
- `kind` (string): 'scalar' or 'vector' (vector = u plane then v plane).
- `lead_hours` (array): Every available lead of this run.
- `source_id` (string)
- `units` (string)
- `variable` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-meltema-weather/meltema#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 68
- 2026-07-31: 68
- 2026-07-30: 67
- 2026-07-29: 67
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 65

## Links

- Remote endpoint: https://meltema.com/mcp
- Website: https://meltema.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-meltema-weather/meltema/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-meltema-weather/meltema/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-meltema-weather/meltema