Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
ICOS atmosphere, ocean and ecosystem greenhouse-gas observations, with citation and DOI per answer
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://mcp.icos-cp.eu/mcpRun this in your terminal
claude mcp add --transport http icos https://mcp.icos-cp.eu/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"icos": {
"url": "https://mcp.icos-cp.eu/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"icos": {
"type": "http",
"url": "https://mcp.icos-cp.eu/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://mcp.icos-cp.eu/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 8, 2026. The maker wrote them, not us; we show them as plain text.
list_datasetsList the ICOS datasets: one per data store, with domain (atmosphere, ocean, ecosystem), time and space coverage, licence and DOI.
search_variablesFind 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_variableOne 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 sli
estimateHow big a selection is -- rows, stations, time span -- without fetching it. Call this before get_data.
get_dataObservations 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.
get_citationHow 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.
aggregateStatistics 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 ro
find_stationsThe 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=.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The publisher (icos-cp.eu) is not the repo owner (ICOS-Carbon-Portal); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 531 ms (HTTP 200)
No sign-in needed
Read 8 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.3.0) reached the registry yesterday.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Brontide agent arena
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
THE MECH ARENA BUILT FOR AI AGENTS. HUMANS WELCOME. Pilot mech duels over MCP, free, no sign-in.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
ICOS carbon and greenhouse-gas observations for AI assistants, over the Model Context Protocol. A thin server over the ICOS zarr proxy (https://zarr.icos-cp.eu): every number comes from the proxy, and every data answer carries the citation, licence and DOI. The plan, and why it is built this way, is docs/plan.md.
Phases 1 and 2: seven read-only tools, five resources, three prompts, and a per-store access policy.
| tool | does |
|---|---|
list_datasets | the stores, with domain, coverage, licence, DOI |
search_variables | variable ids by name, quantity or unit ("methane" finds ch4) |
describe_variable | one variable in full, with how its QC flag is read |
find_stations | the stations carrying a variable: near a point, in a box, by name or country |
estimate | how big a selection is, before fetching it |
get_data | at most 2,000 rows, the total, a CSV download URL for the whole selection, the citation |
get_citation | citation, licence and DOI from the data passport |
uv run icos-mcp # stdio, for a local client uv run icos-mcp --transport streamable-http --port 8090 # http://127.0.0.1:8090/mcp
ICOS_PROXY points it at another proxy (the RC, a test instance).
Over HTTP the server also answers GET / with an HTML page in the style of zarr.icos-cp.eu -- built from what it offers an anonymous caller: the endpoint and how to connect, the public datasets, the tools and prompts, the citation rule (landing.py; ICOS_MCP_PUBLIC_URL sets the endpoint it names, default https://mcp.icos-cp.eu) -- and GET /health.
DEFAULT-DENY: a store is offered only when a rule names it, whatever the proxy behind the server would serve. Without a config file the rules are exactly the public stores of zarr.icos-cp.eu (config/public.json writes them out). ICOS_MCP_CONFIG=/path/to/config.json sets the proxy, the Host header to send it, the base of download links, and an ordered list of store rules, each public or token:
uv run icos-mcp --show-policy # what this config offers, to whom uv run icos-mcp --hash-token TOKEN # the line a tokens_file takes
config/ct122.example.json is the shape for running beside zpd on CT122, where zpd answers for EVERY store on the machine (the shuttle, GlobalView, AGAGE): the public stores by name, those three behind tokens, anything else hidden. A token store is offered to an HTTP caller sending Authorization: Bearer whose SHA-256 is in its tokens_file (plain tokens are never stored); a local stdio caller is the operator and uses ICOS_MCP_TOKEN, which never speaks for an HTTP caller. A hidden store answers exactly as one that does not exist, and the static icos://catalogue resource -- which the protocol does not tell who is asking -- lists the public stores only.
An oauth section in the config makes signing in required over HTTP. Anyone can sign in. The aim is to know who uses the server, not to keep anyone out:
"oauth": {"issuer": "https://sso.fs4vm.icos-cp.eu/realms/icos-test", "audience": "https://mcp.icos-cp.eu"}
The server is only a resource server. ICOS's Keycloak handles the sign-in, through cpauth, Google or ORCID. MCP clients find Keycloak in /.well-known/oauth-protected-resource, register themselves with it and send the user to sign in. A token must be signed by the realm and carry this server's audience, which needs an audience mapper in Keycloak. The store tokens above still work. The landing page and /health stay open, and the stdio operator is never asked to sign in (auth.py).
Signing in also allows a group store rule. The store is offered to members of a Keycloak group, or of a subgroup of one, and to no one else. The groups come from the verified token's groups claim:
{"match": "agage*", "access": "group", "groups": ["agage"], "public_url": "https://agage-zarr.icos-cp.eu"}
Group names are paths below /apps/mcp in the realm: agage is /apps/mcp/agage. That is the only part of a user's groups Keycloak sends this server.
Access is granted and withdrawn in Keycloak, not in the config. A group rule may also list store tokens for scripts. A group rule without an oauth section is refused at load, because nobody could reach it.
In Claude Code:
claude mcp add icos -- uv --directory /path/to/zarrm9/mcp run icos-mcp
Resources: icos://stores/{store}/agent-guide, icos://stores/{store}/croissant, icos://catalogue, icos://llms.txt, icos://data-passport. Prompts: station_record, compare_stations, ocean_region.
uv run pytest # over RECORDED proxy answers (tests/cassette) ICOS_CASSETTE_MODE=record uv run pytest # re-record from the live proxy ICOS_LIVE=1 uv run pytest # live, nothing recorded uv run ruff check src tests conformance/run.sh # the MCP conformance suite (needs Node)
conformance/run.sh starts a local server and runs the MCP project's own conformance suite against it, pinned to 0.1.16 by conformance/package-lock.json. conformance/baseline.yml lists the known failures and why each one fails (mostly the suite's own test fixtures, which a real server doesn't carry). It is read in both directions: a new failure fails the run, and so does an entry that now passes.
eval/questions.json is the DRAFT evaluation set: 30 questions across the three domains, each naming the variable and station a correct answer must use and a truth computed from the proxy at run time. It needs one reviewer per domain before it is relied on; the runner is not written yet.
This server is the ORACLE for the M9 port (mcpd, plan phase 7): its tool names, descriptions and answer shapes are the contract the port is replayed against, so change them deliberately.
Copyright (C) 2026 ICOS ERIC -- Carbon Portal.
This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. See LICENSE.
The DATA this server serves are not covered by this licence: each answer carries the licence of its dataset (ICOS data are CC BY 4.0) and the citation to give with it.