mcp-sofascore
Provides live football match data from Sofascore, including formations, injuries, betting odds, and league positions, enabling natural language queries about matches.
README
MCP Sofascore
An MCP (Model Context Protocol) server that provides live football match data from Sofascore. Connect it to Claude Desktop, Cursor, or any MCP-compatible client.
What it does
Ask Claude about any football match and get:
- Formations
- Injuries and suspensions
- Betting odds
- League positions
- Match date/time
Example:
"Get me the match data for Arsenal vs Man Utd 25 Jan 2026"
Returns:
Arsenal vs Man United — 25 Jan 2026, 17:30 @ Emirates Stadium
Formations:
- Arsenal: 4-3-3 (1st in table)
- United: 4-2-3 (4th in table)
Odds:
- Arsenal win: 1.53
- Draw: 4.50
- Man Utd win: 5.75
Injuries:
- Arsenal: Calafiori (Out)
- United: De Ligt (Out), Dowman (Out), Zirkzee (Doubtful)
Setup
Prerequisites
- Bun
- Serper API key (free tier available)
- Claude Desktop
Install
git clone https://github.com/YOUR_USERNAME/mcp-sofascore.git
cd mcp-sofascore
bun install
bunx playwright install chromium
Configure Claude Desktop
Find your config file:
- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the server:
{
"mcpServers": {
"sofascore": {
"command": "/path/to/bun",
"args": ["/path/to/mcp-sofascore/server.ts"],
"env": {
"SERPER_API_KEY": "your-serper-key"
}
}
}
}
Replace:
/path/to/bunwith output ofwhich bun/path/to/mcp-sofascorewith your actual path
Restart Claude Desktop.
Usage
In any Claude conversation, ask about a match:
- "Get match data for Liverpool vs Chelsea 15 Mar 2026"
- "What are the lineups for Wolves vs Arsenal 18 Feb 2026"
- "Show me injuries for the Manchester derby this weekend"
Include the date for best results - otherwise it may find the wrong match.
How it works
- Searches Google via Serper for the Sofascore match page
- Scrapes the page with Playwright
- Extracts formations, injuries, odds, positions
- Returns structured data to Claude
Tool Definition
| Name | Description |
|---|---|
get_match_data |
Get match info from Sofascore. Input: team names with date (e.g., "Wolves vs Arsenal 18 Feb 2026") |
Tech Stack
- Runtime: Bun
- MCP SDK: @modelcontextprotocol/sdk
- Scraping: Playwright
- Search: Serper API
Limitations
- Only works for matches Sofascore has data for
- Requires date for accurate match lookup
- Scraping may break if Sofascore changes their site structure
License
MIT
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.