openfoot-mcp
It is an MCP server that lets you query real football data from OpenFootAPI — fixtures, results, standings, lineups, match events, shot-level xG, fair odds, and derived context — through an LLM client.
Find entities:
openfoot_searchresolves fuzzy team/competition names to canonical IDs;openfoot_competitionslists supported competitions and season metadata.Matches & tables:
openfoot_matchesreturns fixtures/results filtered by date, competition, team, status, season, with pagination;openfoot_standingsreturns league tables with form.Match detail:
openfoot_match_lineups,openfoot_match_events, andopenfoot_match_xggive starting XIs, goals/cards/subs/VAR/commentary, and shot-by-shot xG with pitch coordinates.Analytics & odds:
openfoot_league_xggives season xG tables and over/underperformance;openfoot_match_contextgives pre/post-match dossiers;openfoot_oddsgives fair 1X2 and over/under probabilities.Workflow prompt: includes
scout_team_formto resolve a team, pull its last 5 matches, and read the xG behind the results.Operations:
openfoot_quotachecks remaining API quota, andopenfoot_healthchecks upstream status without an API key.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@openfoot-mcp What's the xG for the Bayern vs Dortmund match?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
openfoot-mcp
MCP server for the OpenFootAPI football intelligence API. Gives an LLM client real football data — fixtures, standings, lineups, live events, shot-level xG with pitch coordinates, and model-derived fair odds — instead of a hallucinated scoreline.
15 tools, 1 prompt. Node ≥ 20, no build step.
Install
npx openfoot-mcpSet your API key in the environment. Free tier: 5,000 requests/month. Get a key at openfootapi.com/pricing.
Claude Desktop / Claude Code
{
"mcpServers": {
"openfoot": {
"command": "npx",
"args": ["-y", "openfoot-mcp"],
"env": { "OPENFOOT_API_KEY": "of_live_..." }
}
}
}Cursor / Windsurf / any stdio MCP client
Same block, in that client's MCP config file.
Related MCP server: api-football-mcp-server
Tools
Tool | What it returns |
| Supported competitions, season metadata, data source and licence per competition |
| Free-text team/competition name → stable IDs |
| Fixtures and results, filtered by date / competition / team / status / season / round, cursor-paginated |
| Standings table for a competition and season |
| Starting XI, bench, formation |
| Goals, cards, substitutions, commentary timeline |
| One entry per shot: pitch coordinates + xG value |
| Derived context — form, head-to-head, pre-computed signals |
| League xG table: xG for, xG against, over/under-performance vs actual goals |
| Bookmaker benchmark + implied fair probabilities. Informational, not betting advice |
| Remaining monthly quota — this call does not consume quota |
| Reachability check. Works without an API key |
Prompt: scout_team_form — resolve a team, pull its last 5 matches, read the xG behind the results.
Start with openfoot_search to resolve IDs. Guessing IDs wastes quota: 404s and empty results are metered like any other request.
Coverage, stated honestly
The catalogue lists 120 competitions. Depth is not uniform, and the catalogue is wider than the deep coverage.
Deepest: Bundesliga, 2. Bundesliga, DFB Pokal, Superliga României
Expanded European: Eredivisie, Primeira Liga, Süper Lig, Pro League, Scottish Premiership
Historical / analytics only: Premier League, La Liga, Serie A, Ligue 1 (xG is Understat-derived)
Call openfoot_competitions and check your league before you build on it.
Quota behaviour
Free: 5,000 requests/month, 60 req/min. Developer $14/month: 250,000 requests/month, 100 req/min, includes xG, shot maps, lineups, live events and fair odds. Pro $39/month: 2,000,000/month, 250 req/min.
No overage billing. When the quota is spent the API returns 429; this server surfaces that as a
quota_or_rate_limiterror rather than an empty result.Quota resets on the 1st of the month, UTC.
Every request is metered, including 404s and empty results.
When this is the wrong tool
High-frequency live polling across many competitions. A monthly quota is the wrong shape for it — a per-day or per-second plan elsewhere will cost you less.
Leagues outside the deep-coverage list above.
You need a contractual SLA, uptime credits or a named support contact. Not offered at these prices.
Development
npm install
npm run smoke # boots the server over stdio, lists tools, calls healthnpm run smoke works without an API key: openfoot_health returns live status, and a key-gated tool returns a readable missing_api_key error so you can tell "not configured" from "broken".
MIT.
Available Tools
12 toolsopenfoot_competitionsList competitionsA
List the competitions OpenFootAPI supports, with IDs, country codes, tiers and provider coverage. Use this first when you need a valid competition ID.
Inputs: no named parameters.
openfoot_healthCheck upstream healthA
Check the operational status of OpenFootAPI without authentication.
Inputs: no named parameters.
openfoot_league_xgGet league xG analyticsA
Season-level Expected Goals analytics for a league — teams ranked by xG generated, xG conceded, over/underperformance vs real goals, and shot efficiency.
Inputs: league (required), season.
openfoot_match_contextGet match context dossierA
A complete pre-match or post-match dossier assembled for analysis: recent form, Elo delta, rest days, head-to-head record and model-derived fair match probabilities.
Inputs: matchId (required).
openfoot_matchesList matchesA
List fixtures and results with scores, kickoff times, status and teams. Filter by competition, team, status, date or season.
Inputs: to, from, team, limit, +3 more.
openfoot_match_eventsGet match eventsA
Timeline of events in a match: goals, assists, yellow/red cards, substitutions, VAR checks, plus live minute-by-minute text commentary.
Inputs: matchId (required).
openfoot_match_lineupsGet match lineupsA
Confirmed starting XI, benches and formations for a match.
Inputs: matchId (required).
openfoot_match_xgGet match shot map & xGA
Shot-level Expected Goals data with coordinates on the pitch, shot type, situation (open play, penalty, corner), outcome and cumulative xG.
Inputs: matchId (required).
openfoot_oddsGet match oddsB
Fair 1X2 and over/under 2.5 probabilities derived from underlying team form, Elo delta and xG performance.
Inputs: date, matchId, competition.
openfoot_quotaCheck API quotaA
Check your API key's tier, monthly request allowance, requests used this month and reset date.
Inputs: no named parameters.
openfoot_searchSearch teams and competitionsA
Search for teams or competitions by fuzzy name to find their canonical OpenFootAPI IDs.
Inputs: q (required), type.
openfoot_standingsGet standingsA
Get the league table for a competition — rank, points, played, won, drawn, lost, goals for/against, goal difference and recent form.
Inputs: competition (required), season.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Each tool targets a distinct data domain, from standings and lineups to events and xG. Minor overlap exists between match_context and odds since both derive probabilities, but the descriptions clarify that context is a broader dossier while odds is dedicated betting-market output.
All tools follow a consistent openfoot_ prefix followed by a clear resource or action name, using snake_case throughout. Whether a tool describes matches, standings, or quota, the naming pattern is predictable and unambiguous.
Twelve tools is a well-scoped number for a football data API. Each tool represents a meaningful data product, including meta tools like quota and health, with no redundant or filler endpoints.
The surface covers the core football data workflow: identifying competitions, searching teams, fetching matches, standings, lineups, events, xG, and odds. It lacks detailed team or player profile endpoints, but for the apparent match-analysis focus, the coverage is strong with only minor gaps.
Maintenance
Related MCP Connectors
Football fixtures, standings, and odds intelligence for AI agents.
Real-time data API for AI Agents: stocks, weather, forex, logistics, search, scrape, news, IP.
NFL analytics tools for AI agents: stats, fantasy, injuries, schedules, and advanced analysis.
Historical football results, draws and no-draw streaks. 11 read-only tools, 6 need no API key.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides tools to query football match data, odds, standings, and team statistics via natural language, integrating with the football-scraper-api.-
- FlicenseNot gradedqualityDmaintenanceEnables natural language querying of football/soccer data via the API-Football service, providing access to leagues, teams, players, fixtures, standings, and statistics.2-
- AlicenseAqualityCmaintenanceEnables AI assistants to query live football data, including fixtures, live scores, standings, statistics, betting odds, and full odds movement history for corner and card lines.1115 npmMIT
- AlicenseAqualityBmaintenanceProvides football fixtures, real results, and bet settlement with odds arithmetic, enabling AI agents to devig markets, evaluate prices, and settle picks without an API key.7MIT