# ICOS carbon and greenhouse-gas observations (remote · mcp.icos-cp.eu)

ICOS atmosphere, ocean and ecosystem greenhouse-gas observations, with citation and DOI per answer

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.icos-cp.eu`: 73/100 (this document), [markdown](https://verifymcp.io/servers/eu-icos-cp-icos/mcp.md), [page](https://verifymcp.io/servers/eu-icos-cp-icos/mcp)

## Channel facts

- Endpoint: `https://mcp.icos-cp.eu/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## 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 2026-11-05.

- **Endpoint Security**: 77/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2357 tokens (~214/item across 11 items; 8 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 52% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the ICOS carbon and greenhouse-gas observations MCP server?

ICOS carbon and greenhouse-gas observations is a hosted endpoint at https://mcp.icos-cp.eu/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http eu-icos-cp-icos 'https://mcp.icos-cp.eu/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "eu-icos-cp-icos": {
      "url": "https://mcp.icos-cp.eu/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "eu-icos-cp-icos": {
      "type": "http",
      "url": "https://mcp.icos-cp.eu/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.eu-icos-cp-icos]
url = "https://mcp.icos-cp.eu/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "eu-icos-cp-icos": {
      "type": "remote",
      "url": "https://mcp.icos-cp.eu/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add eu-icos-cp-icos --url 'https://mcp.icos-cp.eu/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  eu-icos-cp-icos:
    url: "https://mcp.icos-cp.eu/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "eu-icos-cp-icos": {
      "Transport": "http",
      "Url": "https://mcp.icos-cp.eu/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add eu-icos-cp-icos -t streamable-http -u 'https://mcp.icos-cp.eu/mcp'
```

### Other

```json
{
  "mcpServers": {
    "eu-icos-cp-icos": {
      "type": "http",
      "url": "https://mcp.icos-cp.eu/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.

### 2026-11-04 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 72, +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.

### 2026-10-31 (score 71, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-30 (score 70)

First indexed and scored.

## MCP tools (8)

### `list_datasets` (~41 tokens)

List the ICOS datasets: one per data store, with domain (atmosphere,
    ocean, ecosystem), time and space coverage, licence and DOI.

Output parameters:

- `datasets` (array)

### `search_variables` (~130 tokens)

Find variable ids in the ICOS catalogue by name, quantity or unit.
    The ids are what estimate and get_data take.  Primary measurements come
    before their companions (standard deviation, value counts, flags).

Input parameters:

- `domain`: atmosphere, ocean or ecosystem
- `limit` (integer)
- `store`: limit to one store, e.g. icos-obspack.zarr
- `text` (string, required): what to look for: a gas, a quantity or a name, e.g. 'co2', 'methane', 'net ecosystem exchange', 'fCO2'

Output parameters:

- `n_matches` (integer)
- `variables` (array)

### `describe_variable` (~94 tokens)

One variable in full: names, unit, which dataset, its coverage, how its
    quality flag is read, licence and DOI.  For a multi-dimensional variable
    read through zarr (access 'zarr'), its axes with their labels, the slice
    /query serves (prescribed) and an xarray line for any other slice.

Input parameters:

- `id` (string, required): a variable id from search_variables

Output parameters:

- `access` (string): query: estimate/get_data/aggregate serve it; zarr: a multi-dimensional variable (e.g. the ONEFlux NEE cube) read with xarray -- see zarr_recipe, and `prescribed` for its /query slice
- `axes`: zarr variables: each extra axis and its labels
- `dataset_title` (string)
- `doi`
- `domain`
- `id` (string)
- `license`
- `long_name`
- `name` (string)
- `prescribed`: zarr variables: the id of the preferred slice /query serves
- `quality_control`: how the store's QC flag is read; apply_qc=true applies the recommended rule
- `quality_flag`
- `query_kind` (string): station_time (series at stations), obs_table (ship/cruise observations) or grid (gridded product)
- `store` (string)
- `time_coverage_end`
- `time_coverage_start`
- `unit`
- `variants`: the multi-dimensional variables this one is the PRESCRIBED slice of; their other slices are read through zarr (describe_variable on one gives the recipe)
- `vocabulary_uri`
- `zarr_recipe`

### `estimate` (~213 tokens)

How big a selection is -- rows, stations, time span -- without fetching
    it.  Call this before get_data.

Input parameters:

- `apply_qc` (boolean): DEFAULT TRUE: drop the observations the store's recommended quality control rejects; false keeps every observation, flagged ones included
- `cruise`: cruise expocodes, a list or a string; ocean observation tables only
- `end`: ISO date or datetime, EXCLUSIVE
- `height_max`
- `height_min`
- `id` (string, required): a variable id from search_variables
- `lat_max`
- `lat_min`
- `lon_max`
- `lon_min`
- `start`: ISO date or datetime, inclusive (2025-01-01)
- `station`: station ids -- a list, or one id (or several, comma-separated) as a string; CASE-SENSITIVE: HTM150 (trigram + sampling height) for atmosphere, SE-Htm for FLUXNET sites

Output parameters:

- `est_bytes`
- `exact` (boolean)
- `id` (string)
- `n_stations`
- `note`
- `rows`: rows the selection holds; None when only an upper bound is known
- `rows_at_most`
- `time_max`
- `time_min`

### `get_data` (~269 tokens)

Observations for one variable, filtered by box, time, station, cruise,
    height and quality control.  Returns at most max_rows rows as a table,
    the total, a download URL for the whole selection, and the citation the
    user must be given with any use of the data.

Input parameters:

- `apply_qc` (boolean): DEFAULT TRUE: drop the observations the store's recommended quality control rejects; false keeps every observation, flagged ones included
- `cruise`: cruise expocodes, a list or a string; ocean observation tables only
- `end`: ISO date or datetime, EXCLUSIVE
- `height_max`
- `height_min`
- `id` (string, required): a variable id from search_variables
- `lat_max`
- `lat_min`
- `lon_max`
- `lon_min`
- `max_rows` (integer): rows to return; the whole selection is at download_url
- `start`: ISO date or datetime, inclusive (2025-01-01)
- `station`: station ids -- a list, or one id (or several, comma-separated) as a string; CASE-SENSITIVE: HTM150 (trigram + sampling height) for atmosphere, SE-Htm for FLUXNET sites

Output parameters:

- `citation`
- `columns` (array)
- `download_complete` (boolean): false when no set of links could be planned to cover the whole selection; the note says what is missing
- `download_url` (string): the selection as CSV when it fits one download; when it does not, the FIRST of download_urls
- `download_urls`: when the selection is larger than one download (the proxy caps an answer at 500,000 rows): one CSV link per time window, together the WHOLE selection -- give the user all of them
- `id` (string)
- `note`
- `rows` (array)
- `rows_returned` (integer)
- `rows_total`: rows in the whole selection, when known
- `truncated` (boolean)

### `get_citation` (~197 tokens)

How to cite a variable's data: the citation text, licence and DOI from
    its data passport, and -- for a selection (stations, a time window, a
    box) -- every data object it came from, in full.  Data answers carry a
    short citation and only the COUNT of their sources; this lists them.

Input parameters:

- `end`: ISO date or datetime, EXCLUSIVE
- `id` (string, required): a variable id from search_variables
- `lat_max`
- `lat_min`
- `lon_max`
- `lon_min`
- `start`: ISO date or datetime, inclusive (2025-01-01)
- `station`: station ids -- a list, or one id (or several, comma-separated) as a string; CASE-SENSITIVE: HTM150 (trigram + sampling height) for atmosphere, SE-Htm for FLUXNET sites

Output parameters:

- `citation`
- `doi`
- `license`
- `license_url`
- `n_sources`: how many data objects the selection came from; in a data answer their citations are listed only when there are three or fewer -- get_citation (with the same stations) lists them all
- `selection_id`: stable id of this exact selection over this exact store version
- `sources`: the citation of each data object the selection came from -- what to cite when there is no collection citation (near-real-time data)
- `store_version`

### `aggregate` (~391 tokens)

Statistics over a WHOLE selection, computed on the server: count, mean,
    min, max, sum and standard deviation of one variable, overall or per
    station, year, month or day.  Use this for any average, total, range or
    trend instead of reading rows.  Any size: a selection over 500,000 rows
    is split by time on the server and merged exactly.  `std` is the
    POPULATION standard deviation (ddof 0).  `sum` adds the values as
    stored, which is a total only for values that are themselves totals per
    row: summing a RATE (umol m-2 s-1 per half-hour, gC m-2 d-1 per day)
    or a concentration gives no physical quantity -- for a flux total
    multiply the mean by the period.

Input parameters:

- `apply_qc` (boolean): DEFAULT TRUE: drop the observations the store's recommended quality control rejects; false keeps every observation, flagged ones included
- `by` (string): the groups: none (one result), station, a period, or both
- `cruise`: cruise expocodes, a list or a string; ocean observation tables only
- `end`: ISO date or datetime, EXCLUSIVE
- `height_max`
- `height_min`
- `id` (string, required): a variable id from search_variables
- `lat_max`
- `lat_min`
- `lon_max`
- `lon_min`
- `start`: ISO date or datetime, inclusive (2025-01-01)
- `station`: station ids -- a list, or one id (or several, comma-separated) as a string; CASE-SENSITIVE: HTM150 (trigram + sampling height) for atmosphere, SE-Htm for FLUXNET sites

Output parameters:

- `by` (string)
- `citation`
- `download_complete` (boolean)
- `download_url` (string)
- `download_urls`
- `groups` (array): one entry per group: its keys (station, period), n (finite values), and mean, min, max, sum, std over them (null when n is 0)
- `id` (string)
- `n_groups` (integer)
- `note`
- `rows_used` (integer)
- `unit`
- `variable` (string)

### `find_stations` (~186 tokens)

The stations that carry a variable: id, name, position, sampling height,
    country, ecosystem -- near a point (sorted by distance), in a box, by name
    or by country.  The ids are what estimate and get_data take as station=.

Input parameters:

- `country`: two-letter code, e.g. SE
- `id` (string, required): a station-based variable id from search_variables
- `lat_max`
- `lat_min`
- `limit` (integer)
- `lon_max`
- `lon_min`
- `near_lat`: search around this point, with near_lon and radius_km
- `near_lon`
- `radius_km` (number)
- `text`: part of a station's id or name, e.g. 'Hyltemossa', 'HTM', 'Hyy'

Output parameters:

- `n_matches` (integer)
- `stations` (array)
- `variable` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/eu-icos-cp-icos/mcp#diagnostics

## Score history

- 2026-11-05: 73
- 2026-11-04: 73
- 2026-11-03: 72
- 2026-11-02: 72
- 2026-11-01: 71
- 2026-10-31: 71
- 2026-10-30: 70

## Common questions

### What is the ICOS carbon and greenhouse-gas observations MCP server?

ICOS carbon and greenhouse-gas observations is an MCP server listed in the public MCP registry as eu.icos-cp/icos. ICOS atmosphere, ocean and ecosystem greenhouse-gas observations, with citation and DOI per answer. This page covers its hosted endpoint (https://mcp.icos-cp.eu/mcp).

### Is the ICOS carbon and greenhouse-gas observations MCP server safe to use?

ICOS carbon and greenhouse-gas observations scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ICOS carbon and greenhouse-gas observations MCP server expose?

ICOS carbon and greenhouse-gas observations exposes 8 tools: list_datasets, search_variables, describe_variable, estimate, get_data, and 3 more. Their descriptions and schemas cost roughly 1,521 tokens of context every time the server is loaded.

### Does the ICOS carbon and greenhouse-gas observations MCP server require authentication?

No. We connected to ICOS carbon and greenhouse-gas observations without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ICOS carbon and greenhouse-gas observations MCP server still maintained?

ICOS carbon and greenhouse-gas observations is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.icos-cp.eu/mcp
- Website: https://mcp.icos-cp.eu/
- Changelog RSS feed: https://verifymcp.io/servers/eu-icos-cp-icos/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/eu-icos-cp-icos/mcp.json
- HTML version of this page: https://verifymcp.io/servers/eu-icos-cp-icos/mcp