ICOS carbon and greenhouse-gas observations MCP Server

by icos-cp Your server? Claim it

answering

ICOS carbon and greenhouse-gas observations is answering right now. Last checked 4 min ago. It exposes 8 tools. Last commit 9 Nov 2026.

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

Uptime history 11 days of history

11 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

62 ms

Response time

average over 24h

Stars

last commit 9 Nov 2026

What changed 9

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 6 November 2026. No other catalogue keeps this.

7 Nov 6 tools changed the parameters they ask for aggregate, estimate, find_stations and 3 more

7 Nov a tool changed version

5 Nov 2 tools changed the parameters they ask for aggregate, get_data

What the code does

We read the source, 14 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable src/icos_mcp/cassette.py:34

        return os.path.join(self.dir, f"{key}.json")

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://mcp.icos-cp.eu/mcp

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 8

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

aggregate

aggregate

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.

citation

get_citation

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.

data

get_data

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.

datasets

list_datasets

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

describe

describe_variable

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.

estimate

estimate

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

stations

find_stations

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=.

variables

search_variables

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).

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.icos-cp.eu/mcp	streamable-http	answering	59 ms	4 min ago

Alternatives to ICOS carbon and greenhouse-gas observations

same job, measured the same way

Fr Eli MCP

by matematicsolutions

MCP server for French Legifrance (PISTE): legislation and case law with citations and ECLI.

173 installs/wk local only

Lead Green

by leadgreen

GPU energy per million output tokens by model, GPU and configuration, with grid carbon by country.

191 installs/wk local only

Company Career Pages Jobs

by rafi-siddiq

Open jobs with salaries from Workday, Greenhouse, Lever, Ashby and 3 more careers-page systems.

answering

ATS Job Postings with Salaries (Yugenox)

by arpitgandhi1934

Career-site jobs from Workday, Greenhouse, Lever, Ashby, iCIMS and more, with salaries where posted.

answering

Fermat 360

by fermat360

Dutch legal AI for law firms: answers from Dutch case law, legislation and EU law, with citations.

answering

Wattindex

by cloudcorprecords

GPU energy per million output tokens by model and GPU, with grid carbon intensity.

321 installs/wk local only

ABS · AI Business System

by ucai

Lean operations knowledge base built on DBS: cited answers, tool cards, plans and diagnoses.

answering

Veritasgraph

by bibinprathap

Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.

556 installs/wk local only

ICOS carbon and greenhouse-gas observations — questions

Answers built from our own checks of this server.

What can ICOS carbon and greenhouse-gas observations do?

It exposes 8 tools, read directly from the server on our last check. Among them: aggregate, describe_variable, estimate, find_stations, get_citation, get_data and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is ICOS carbon and greenhouse-gas observations working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 62 ms. The bar chart above shows every period we have measured.

How do I connect ICOS carbon and greenhouse-gas observations?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does ICOS carbon and greenhouse-gas observations need an API key?

No. ICOS carbon and greenhouse-gas observations completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is ICOS carbon and greenhouse-gas observations?

It answers our handshake in 62 ms on average, which is faster than 99% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is ICOS carbon and greenhouse-gas observations open source?

The code is open source: it is published under the GPL-3.0 licence, written in Python and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at mcp.icos-cp.eu, which runs on its operator's own terms.