FIFA World Cup 2026 AI Assistant

A conversational AI assistant for FIFA World Cup 2026 built with Claude and the Model Context Protocol (MCP). Ask about today's matches, group standings, results, and get journalist-style match summaries.

Live demo: https://worldcup-mcp-gjg7.onrender.com

What is MCP?

Model Context Protocol (MCP) is a standard that lets AI models like Claude connect to external data sources and tools. Instead of Claude only knowing what's in its training data, MCP lets it fetch live data and take actions — like reading today's World Cup scores.

Related MCP server: mcp-football

Features

• Live match scores and fixtures for today

• Group stage standings (calculated from results)

• Match results with goalscorers and times

• Filter results by round (e.g. Quarter-final, Group A)

• Journalist-style match summaries powered by Claude

• Web chat UI with FIFA-themed design

Project Structure

worldcup-mcp/
├── mcp_server.py     # MCP server — tools and prompts
├── api.py            # FastAPI backend + WebSocket chat
├── main.py           # Terminal chat client
├── static/
│   └── index.html    # Web UI (navy + gold FIFA theme)
├── render.yaml       # Render deployment config
└── pyproject.toml    # Python dependencies

MCP Primitives Used

Data Source

Match data comes from openfootball/world-cup.json — a free, open-source dataset with no API key required.

Setup

Prerequisites

• Python 3.9+

• uv package manager

• Anthropic API key (get one here)

Run locally

1. Clone the repo:

git clone https://github.com/sanketjoshi2012/worldcup-mcp.git
cd worldcup-mcp

2. Install dependencies:

uv sync

3. Create a .env file:

ANTHROPIC_API_KEY="your-api-key-here"

4. Run the web app:

uv run uvicorn api:app --port 8000 --reload

Then open http://localhost:8000 in your browser.

Or run the terminal version:

uv run main.py

Deployment

This project is configured for deployment on Render via render.yaml.

1. Push to GitHub

2. Connect repo on Render

3. Add ANTHROPIC_API_KEY as an environment variable

4. Deploy

Built With

• Anthropic Claude — AI model

• MCP Python SDK — Model Context Protocol

• FastAPI — Web backend

• uv — Python package manager

• openfootball — World Cup data