matchday-mcp

matchday-mcp

Live football/soccer data from top European leagues, enabling queries for standings, fixtures, scorers, and team comparisons via natural language.

Category
Visit Server

README

⚽ matchday-mcp

npm version CI License: MIT MCP

A Model Context Protocol server that gives any MCP client (Claude Desktop, Claude Code, …) live football/soccer data — standings, fixtures, results, top scorers and team comparisons across Europe's top leagues.

Built with TypeScript + Zod, backed by the free football-data.org API.

Ask Claude "How is Real Madrid doing this season?" or "Compare Arsenal and Liverpool's recent form" and it answers with real data through these tools.

🔗 Live playground: matchday-mcp-web.vercel.app — an interactive dashboard built with SvelteKit + Svelte 5 that runs on this server's data layer.

Demo

> get_standings  { "competition": "La Liga" }

**La Liga standings — 2025**
 #  Team                         P   W  D  L   GD  Pts
 1  FC Barcelona               38  31  1  6   59   94
 2  Real Madrid CF             38  27  5  6   42   86
 3  Villarreal CF              38  22  6 10   26   72
 4  Club Atlético de Madrid    38  21  6 11   18   69
 ...

<!-- A short GIF of the tools running inside Claude Desktop will live here. -->

Tools

Tool What it does
get_standings League table for a competition (position, W/D/L, GD, points).
get_matches Matches for a competition, filterable by status and matchday.
get_top_scorers Top scorers for a competition.
find_team Look up a club by name (country, stadium, founded year, competitions).
get_team_matches A club's recent results or upcoming fixtures, with a W/D/L form string.
compare_teams Compare two clubs by recent form (last 5) and W/D/L tally.

Competitions (free tier): Premier League (PL), La Liga (PD), Bundesliga (BL1), Serie A (SA), Ligue 1 (FL1), Eredivisie (DED), Primeira Liga (PPL), Championship (ELC), Brazil Série A (BSA), Champions League (CL), World Cup (WC), European Championship (EC). You can pass a competition by name ("Premier League") or code ("PL").

Quick start (Claude Desktop)

  1. Get a free API token at football-data.org/client/register (takes ~1 minute).

  2. Add the server to your claude_desktop_config.json:

    {
      "mcpServers": {
        "matchday": {
          "command": "npx",
          "args": ["-y", "matchday-mcp"],
          "env": { "FOOTBALL_DATA_TOKEN": "your_free_token_here" }
        }
      }
    }
    
  3. Restart Claude Desktop. Ask it about standings, fixtures, scorers or team form.

Works the same in any MCP client. In Claude Code: claude mcp add matchday -e FOOTBALL_DATA_TOKEN=your_token -- npx -y matchday-mcp.

Development

git clone https://github.com/reiorozco/matchday-mcp.git
cd matchday-mcp
npm install

export FOOTBALL_DATA_TOKEN=your_free_token   # required to hit the live API

npm run dev        # run the server over stdio (tsx)
npm test           # run the unit tests (no token needed — fetch is mocked)
npm run typecheck  # tsc --noEmit
npm run build      # bundle to dist/ with tsup
Variable Required Description
FOOTBALL_DATA_TOKEN yes Free token from football-data.org.

Design notes

  • Zod-validated tools. Every tool input is described and validated with Zod, so the model gets clear schemas and bad arguments fail fast with readable errors.
  • Caching + rate-limit resilience. The free tier allows 10 req/min and returns HTTP 429 when exceeded, so the client adds an in-memory TTL cache plus bounded retry/backoff.
  • Lazy team index. football-data.org has no team-name search, so the client builds a name → id index across the domestic leagues one league at a time with early exit — a well-known club costs 1–2 requests, not a full sweep. Name resolution is ranked (exact → starts-with → shortest name), so "Barcelona"FC Barcelona, not RCD Espanyol.
  • Off-season aware. In the off-season the API's "current season" already points at the next, not-yet-started season (empty tables), so the default season rolls over in August.
  • Pure, testable handlers. Tool logic lives in plain functions returning strings; the MCP wiring is a thin layer on top. The same data layer powers the web playground (source).

Data

Data from football-data.org. This project is not affiliated with football-data.org or any league.

License

MIT © Reinaldo Orozco

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured