ICOS MCP server

• Registry nameeu.icos-cp/icosverified in the MCP registry

The registry name sits under icos-cp.eu. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-30
• Tools8
• Server calls itselficos
• Server version0.2.0
• Protocol version2025-06-18

On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 531 ms.

• Its tools do download greenhouse gas measurement data from the data portal; compare atmospheric CO2 levels across stations on the ICOS curve, but not estimate air-mass footprints with the STILT calculator.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• What an agent can do with it2 of 3 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer540 ms
• Space in an agent's context≈ 3,033 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsB · 88 of 100
• Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 6 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_datasets

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

• 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).

• 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…

• estimate

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

• 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…

• 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…

• 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=.