nutmeg

IN BETA!

Football data analytics for AI coding tools

Makes your AI agent an expert at football data. It looks up the real docs instead of guessing — qualifier IDs, coordinate systems, API endpoints, method signatures. All verified, all sourced.

Get started

Answer two questions and we'll show you exactly what to install.

What AI coding tool do you use?

What do you want?

Start here

/nutmeg

Describe what you want — it handles the rest

/nutmeg:learn

Concepts, resources, provider docs

Sub-skills auto-dispatched or called directly

/nutmeg:acquire

Fetch and download football data

/nutmeg:wrangle

Transform and reshape data

/nutmeg:compute

Derived metrics (xG, PPDA...)

/nutmeg:analyse

Explore and interpret data

/nutmeg:brainstorm

Visualisation ideation

/nutmeg:review

Check data code and charts

/nutmeg:store

Storage and publishing

/nutmeg:heal

Fix broken scrapers and pipelines

Providers

Provider	Events	Stats	xG	Free?
StatsBomb				Open data
Opta
Wyscout
SportMonks				Free tier
FBref
Understat

football-docs

IN BETA!

Like Context7 for football data

Searchable documentation across 30 football data providers and tools, built for AI coding agents. Covers club and provider APIs including StatsBomb, Wyscout, SportMonks, Impect, SkillCorner, Sportradar, Driblab, ESPN, TheSportsDB, BeSoccer, FMDB Pro, TransferRoom, Opta, public/free sources and the Reep identity register, wearable and sports-science APIs (STATSports, Firstbeat Sports, Hawkin Dynamics, VALD), plus open-source libraries people build with too (kloppy, mplsoccer, socceraction, soccerdata, databallpy, floodlight, fast-forward, unravelsports, and more). Your agent resolves provider names, looks up the real docs, compares provider concepts, resolves football entities across provider IDs, and finds, reads and quotes the papers and posts behind a method, instead of guessing from training data. Works with any MCP client.

3396

searchable chunks

providers + tools

MCP tools

v0.16.1

npm version

GitHub repo npm package

Install

Claude Code

Adds football-docs to the current Claude Code project.

claude mcp add football-docs -- npx -y football-docs@latest

Claude Code user scope

Use this when you want football-docs available across all Claude Code projects.

claude mcp add --scope user football-docs -- npx -y football-docs@latest

MCP JSON

Use this shape in clients that accept MCP server JSON config.

{
  "mcpServers": {
    "football-docs": {
      "command": "npx",
      "args": [
        "-y",
        "football-docs@latest"
      ]
    }
  }
}

Requires Node 22.13+. Restart your client, then ask use football-docs to find where xT comes from.

Tools

search_docs

Full-text search across all providers

resolve_provider_id

Resolve provider names and aliases

get_provider_docs

Retrieve docs for a resolved provider

list_providers

See all indexed providers

compare_providers

Compare how providers handle concepts

request_update

Flag outdated docs or request new ones

resolve_entity

Map players, teams, matches and more across provider IDs via Reep

search_papers

Search papers in OpenAlex, arXiv, SportRxiv and your Zotero library

get_paper

Look up a paper by DOI, arXiv or OpenAlex ID, with its licence

get_web_source

Read a blog post or web page, dated by the Wayback Machine

read_paper

Read an open paper by section, with its licence

match_quote

Check that a quote actually appears in its source

add_local_paper

Add a PDF you have access to your paper library

forget_paper

Remove one paper from your library

purge_cache

Clear your whole paper library

Example queries

"Where does xT come from?"
"How does StatsBomb represent shots?"
"Compare Opta and Wyscout coordinates"
"Does SportMonks have xG?"
"How does SPADL represent a tackle?"
"Quote how the VAEP paper values an action"

Indexed providers

SportMonks

568 chunks

Sportradar

481 chunks

VALD

318 chunks

fast-forward

250 chunks

StatsBomb

244 chunks

unravelsports

202 chunks

Wyscout

165 chunks

floodlight

144 chunks

kloppy

126 chunks

Firstbeat Sports

79 chunks

Impect

79 chunks

Opta

73 chunks

STATSports

70 chunks

Hawkin Dynamics

69 chunks

mplsoccer

65 chunks

databallpy

63 chunks

Free sources

60 chunks

SkillCorner

51 chunks

TransferRoom

45 chunks

soccerdata

40 chunks

FMDB Pro

37 chunks

socceraction

34 chunks

Driblab

32 chunks

Reep

29 chunks

ESPN

21 chunks

TheSportsDB

20 chunks

BeSoccer

16 chunks

FotMob

5 chunks

Soccerdonna

5 chunks

Transfermarkt

5 chunks

What's new since v0.12.2

v0.16.1 shipped — on npm now

Find, read and quote papers shipped

Your agent can now find the research behind a method and check it before citing it. search_papers searches OpenAlex, arXiv and SportRxiv, read_paper reads open-access papers in full, and match_quote confirms a quote actually appears in the source. get_web_source reads blog posts too: ask where xT comes from and it finds Karun Singh’s original post, shows it was online by February 2019 via the Wayback Machine, and quotes the sentence where he named it.

Paid papers, the honest way shipped

Add a PDF you already have access to with add_local_paper, or point it at your Zotero library. football-docs never logs in anywhere on your behalf and only returns short passages from those papers. Paper text stays on your machine, and FOOTBALL_DOCS_PAPERS=off turns every paper and web request off.

Wearables and sports science shipped

STATSports, Firstbeat Sports, Hawkin Dynamics and VALD join the index, with endpoint, field and metric tables generated from each vendor’s public specs and checked in CI.

Checked against the sources shipped

The Opta, StatsBomb and SportMonks ID tables are now checked against each provider’s own sources on every change. Search marks results that only partly match, and says when you ask about something that is not indexed, and why.

Always current shipped

Doc fixes reach your install within a day with no new version: the server checks for a newer, signed docs index and uses it from the next tool call. It runs on Node’s built-in SQLite and is tested on macOS, Windows and Linux.

campos

IN BETA!

React components for football, typed and agent-native

23 React chart components, 10 data-provider adapters, one canonical coordinate frame, zero-config defaults. Typed from schema to render. Every chart is agent-discoverable via a static JSON registry at campos.withqwerty.com/r/ — nutmeg proposes and composes campos charts automatically when it detects a React project. Docs and live demos at campos.withqwerty.com.

chart components

data adapters

2333

tests

npm packages

Drives from nutmeg, automatically

When nutmeg detects a React project (package.json contains react or @withqwerty/campos-react), it loads a shared bridge doc, fetches the registry above, and proposes campos charts with real capability data per provider. Chart output, adapter selection, and recipe suggestion all route through the live catalogue — no hallucinated props, no training-data drift. See nutmeg on GitHub for the bridge reference.

nutmeg

Get started

football-docs

campos

Start building with football data