nutmeg
Health Uyari
- No license — Repository has no license file
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 7 GitHub stars
Code Basarisiz
- exec() — Shell command execution in mcp/football-docs-server/src/ingest.ts
Permissions Gecti
- Permissions — No dangerous permissions requested
This is a Model Context Protocol (MCP) server that acts as a knowledge base for football data analytics. It provides AI coding assistants with verified, up-to-date documentation for various sports data providers like Opta, StatsBomb, and Wyscout so they can write accurate data processing code.
Security Assessment
The overall risk is rated as Medium. A code scan flagged an `exec()` shell command execution within the source code (`mcp/football-docs-server/src/ingest.ts`). While this is commonly used during the build or documentation ingestion process, any dynamic command execution inherently increases the attack surface. The server does not request overtly dangerous system permissions. However, as an MCP server, it naturally interfaces with your local AI environment, and the tool requires network requests to fetch live documentation and API endpoints. No hardcoded secrets were identified, but users should always be cautious about passing their personal API keys (e.g., for SportMonks) to the tool.
Quality Assessment
The project is actively maintained, with its most recent code push occurring today. However, it currently has extremely low community visibility, boasting only 7 GitHub stars. Because of this low adoption, the codebase has not been broadly vetted by the open-source community. A significant concern for enterprise or open usage is the complete lack of a license file. Without a defined license, all rights are technically reserved by the author, meaning the legal terms of use and redistribution are ambiguous.
Verdict
Use with caution — while the project is actively maintained and appears safe for personal use, the lack of a software license and the presence of shell execution commands mean you should review the codebase before integrating it into professional environments.
Football data analytics toolkit for Claude Code. Covers Opta, StatsBomb, Wyscout, SportMonks, and free sources.
nutmeg
A Claude Code plugin that makes Claude an expert at football data analytics.
Who it's for: Anyone who works with football data — analysts, developers, journalists, researchers, hobbyists. If you've ever spent an hour figuring out which Opta qualifier is xG, or why your StatsBomb coordinates are upside down, or how to normalise a heatmap properly, this is for you.
What it does: Gives Claude deep, verified knowledge of football data providers, libraries, and conventions. Claude looks up the actual docs instead of guessing from training data, writes code adapted to your stack, and catches football-specific mistakes in your work.
Why not just ask Claude directly? Claude knows football data exists but its knowledge is frozen and often wrong on specifics — qualifier IDs, API endpoints, coordinate systems, method signatures. These change. nutmeg connects Claude to a live, searchable index of real provider documentation so it gets the details right.
Capabilities
nutmeg gives Claude deep knowledge of football data so it can help you:
- Acquire data from Opta, StatsBomb, Wyscout, SportMonks, FBref, Understat, and more
- Wrangle event streams, transform coordinates, join datasets, handle large files
- Compute derived metrics like xG, PPDA, passing networks, expected threat
- Store data in the right format and publish results via Streamlit, Observable, or static sites
- Analyse matches, players, and teams with statistical rigour
- Learn football analytics concepts, from xG basics to academic research
It adapts to your experience level, preferred programming language, and available data sources.
Install
Full install (Claude Code plugin)
Includes skills, agents, and the football docs MCP server.
# From Claude Code — add the marketplace first (one-time), then install
/plugin marketplace add withqwerty/plugins
/plugin install nutmeg@withqwerty
Skills only (any AI coding agent)
Works with Claude Code, Cursor, Codex, Windsurf, and 40+ other agents via the Agent Skills standard.
npx skills add withqwerty/nutmeg
This installs the 10 skills but not the agents or MCP docs server. For the full experience (searchable provider docs, pipeline builder agent, data reviewer agent), use the plugin install above.
Setup
Run /nutmeg and describe what you want to do. On first run, it creates your profile (experience, tools, data access) so all skills adapt accordingly.
Skills
Most users only need two commands — /nutmeg routes everything else automatically.
Entry points
| Skill | What it does |
|---|---|
/nutmeg |
Start here. Describe what you want — it handles setup, routing, and dispatch |
/nutmeg-learn |
Concepts, resources, provider docs, learning paths |
Sub-skills (auto-dispatched or direct)
These are invoked automatically by /nutmeg based on what you're doing. Power users can call them directly.
| Skill | What it does |
|---|---|
/nutmeg-acquire |
Fetch, scrape, or download data + manage API keys |
/nutmeg-wrangle |
Transform, filter, reshape data |
/nutmeg-compute |
Calculate derived metrics (xG, PPDA, passing networks) |
/nutmeg-analyse |
Explore and interpret football data |
/nutmeg-brainstorm |
Research-backed visualisation ideation and chart design |
/nutmeg-store |
Choose storage format and publishing method |
/nutmeg-review |
Review data code and charts for correctness and conventions |
/nutmeg-heal |
Fix broken scrapers, submit upstream issues |
Football Docs MCP Server
nutmeg includes a searchable index of football data provider documentation. Think Context7 for football data.
# Build the docs index
cd mcp/football-docs-server
npm install
npm run ingest
# The MCP server starts automatically when nutmeg is loaded
Adding provider docs
Drop markdown files in docs/providers/{provider}/ and re-run npm run ingest:
docs/providers/
opta/
event-types.md
qualifiers.md
coordinate-system.md
api-access.md
statsbomb/
event-types.md
data-model.md
...
Providers covered
| Provider | Event data | Stats | xG | Tracking | Free? |
|---|---|---|---|---|---|
| StatsBomb | Yes | Yes | Yes | No | Open data (select comps) |
| Opta/Perform | Yes | Yes | Yes (xGOT too) | Yes | No (unofficial feed exists) |
| Wyscout | Yes | Yes | No | No | No |
| SportMonks | Partial | Yes | No | No | Free tier |
| FBref | No | Yes | Yes (via StatsBomb) | No | Yes (scraping) |
| Understat | No | Partial | Yes | No | Yes (scraping) |
| ClubElo | No | No | No | No | Yes (API) |
License
MIT
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi