Skip to main content
Glama
billychl1

FootballBin MCP Server

by billychl1
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Hybrid

FootballBin MCP Server

npm version MCP Registry License: MIT

A Model Context Protocol (MCP) server that provides AI agents with access to football match predictions for the Premier League and Champions League.

Requirements

  • Node.js 18+ (check with node --version)

Related MCP server: mcp-sofascore

Installation

Option 1: npm (Recommended)

npm install -g footballbin-mcp-server

Option 2: npx (No Install)

npx footballbin-mcp-server

Option 3: Remote Endpoint

No installation required - use the hosted endpoint directly:

https://ru7m5svay1.execute-api.eu-central-1.amazonaws.com/prod/mcp

Quick Start

Claude.ai (Easiest - No Install)

  1. Go to Settings > Connectors

  2. Click Add custom connector

  3. Enter: https://ru7m5svay1.execute-api.eu-central-1.amazonaws.com/prod/mcp

Claude Desktop

Requires Node.js 18+

Step 1: Install globally

npm install -g footballbin-mcp-server

Step 2: Find your Node.js path (must be v18+)

which node && node --version

Step 3: Add to claude_desktop_config.json:

{
  "mcpServers": {
    "footballbin": {
      "command": "/path/to/node",
      "args": ["/path/to/node_modules/footballbin-mcp-server/dist/index.js"]
    }
  }
}

Example configs:

macOS with nvm:

{
  "mcpServers": {
    "footballbin": {
      "command": "/Users/YOU/.nvm/versions/node/v20.x.x/bin/node",
      "args": ["/Users/YOU/.nvm/versions/node/v20.x.x/lib/node_modules/footballbin-mcp-server/dist/index.js"]
    }
  }
}

macOS with Homebrew:

{
  "mcpServers": {
    "footballbin": {
      "command": "/opt/homebrew/bin/node",
      "args": ["/opt/homebrew/lib/node_modules/footballbin-mcp-server/dist/index.js"]
    }
  }
}

Windows:

{
  "mcpServers": {
    "footballbin": {
      "command": "C:\\Program Files\\nodejs\\node.exe",
      "args": ["C:\\Users\\YOU\\AppData\\Roaming\\npm\\node_modules\\footballbin-mcp-server\\dist\\index.js"]
    }
  }
}

Config file location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Other MCP Clients

Use the remote endpoint:

https://ru7m5svay1.execute-api.eu-central-1.amazonaws.com/prod/mcp

Features

  • AI Match Predictions:

    • Half-time score

    • Full-time score

    • Next goal scorer

    • Corner count predictions

  • Supported Leagues:

    • Premier League (EPL)

    • UEFA Champions League (UCL)

  • Key Players: Each match includes key player insights with reasoning

Tool: get_match_predictions

Input Parameters

Parameter

Type

Required

Description

league

string

Yes

premier_league, epl, pl, champions_league, ucl, cl

matchweek

number

No

Matchweek number (defaults to current)

home_team

string

No

Filter by home team (e.g., chelsea, arsenal)

away_team

string

No

Filter by away team (e.g., liverpool, wolves)

Team Aliases

Alias

Maps To

united, mufc

man_utd

city, mcfc

man_city

spurs

tottenham

villa

aston_villa

forest

nottm_forest

palace

crystal_palace

gunners

arsenal

reds

liverpool

blues

chelsea

barca

barcelona

real

real_madrid

Example Response

{
  "league": "premier_league",
  "matchweek": 22,
  "count": 10,
  "app_link": "https://apps.apple.com/app/footballbin/id6757111871",
  "matches": [
    {
      "match_id": "epl_mw22_liv_bur",
      "home_team": "Liverpool",
      "away_team": "Burnley",
      "kickoff_time": "2026-01-17T15:00:00Z",
      "status": "scheduled",
      "predictions": [
        { "type": "Half Time Result", "value": "2:0", "confidence": 75 },
        { "type": "Full Time Result", "value": "4:0", "confidence": 75 },
        { "type": "Next Goal", "value": "Home,Wirtz", "confidence": 75 },
        { "type": "Corner Count", "value": "9:3", "confidence": 75 }
      ],
      "key_players": [
        {
          "player_name": "Florian Wirtz",
          "reason": "12 goals, 14 assists. Liverpool's creative hub."
        }
      ]
    }
  ]
}

Direct API Usage

List Tools

curl -X POST https://ru7m5svay1.execute-api.eu-central-1.amazonaws.com/prod/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'

Get Predictions

curl -X POST https://ru7m5svay1.execute-api.eu-central-1.amazonaws.com/prod/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "get_match_predictions",
      "arguments": {"league": "premier_league"}
    },
    "id": 1
  }'

Registry Links

FootballBin App

Get the full experience with the FootballBin iOS app:

Download on App Store

Features:

  • Live match tracking

  • AI player valuations

  • Detailed match predictions

  • Player news and discussions

Technical Details

  • Protocol: JSON-RPC 2.0 / MCP

  • Transport: stdio (npm) or HTTPS (remote)

  • Runtime: Node.js 20+

Error Codes

Code

Meaning

-32700

Parse error

-32600

Invalid request

-32601

Method not found

-32602

Invalid params

License

MIT License - see LICENSE file.

Links

Available Tools

1 tool
get_match_predictionsC

Get AI-powered predictions for Premier League and Champions League matches including half-time score, full-time score, next goal scorer, and corner predictions.

ParametersJSON Schema
NameRequiredDescriptionDefault
leagueYesLeague to get predictions for. Accepts: "premier_league", "epl", "pl", "champions_league", "ucl", "cl"
matchweekNoMatchweek number (optional, defaults to current matchweek)
home_teamNoFilter by home team name (optional, e.g., "chelsea", "arsenal", "man_utd")
away_teamNoFilter by away team name (optional, e.g., "liverpool", "wolves")

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'AI-powered predictions' but lacks details on rate limits, authentication needs, data freshness, confidence levels, or response format. For a tool with no annotations, this leaves critical behavioral traits unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose, scope, and prediction types without any wasted words. It is appropriately sized and front-loaded with essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It does not address behavioral aspects like rate limits or authentication, nor does it explain the return values or prediction format. For a tool with no structured data beyond the input schema, more contextual information is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional parameter semantics beyond what the schema provides, such as explaining interactions between parameters or usage examples. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('Get AI-powered predictions') and resources ('Premier League and Champions League matches'), including the types of predictions (half-time score, full-time score, etc.). It distinguishes itself from hypothetical alternatives by specifying the leagues and prediction types, though there are no actual sibling tools to differentiate from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual usage. It lists what the tool does but offers no explicit when/when-not instructions or comparisons to other tools, which is a significant gap in usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against for patterns or conventions.

Tool Count2/5

One tool is too few for a server focused on football match predictions, as it suggests a limited scope that may not cover related operations like historical data, team statistics, or user preferences. This feels thin for the apparent domain.

Completeness2/5

The server is severely incomplete for football predictions, as it only provides predictions without supporting tools for data retrieval, updates, or other predictive features like odds analysis or match scheduling. This creates significant gaps for agent workflows.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • football-scraper-mcp

    bitsahara
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides tools to query football match data, odds, standings, and team statistics via natural language, integrating with the football-scraper-api.

  • mcp-sofascore

    cyberkillua
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides live football match data from Sofascore, including formations, injuries, betting odds, and league positions, enabling natural language queries about matches.
    1

  • api-football-mcp-server

    dankniight
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables natural language querying of football/soccer data via the API-Football service, providing access to leagues, teams, players, fixtures, standings, and statistics.
    3

  • footballcharts-mcp

    ddevetak
    A
    license
    A
    quality
    B
    maintenance
    Provides AI assistants with live football data for 90+ leagues including tables, results, fixtures, model probabilities, and Monte Carlo season projections from football-charts.com.
    10
    66
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/billychl1/footballbin-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server