PlayerElo MCP server
Provides MCP access to PlayerElo's football analytics, including player/coach Elo ratings, match predictions, value bets, and transfer fit scores.
README
PlayerElo MCP server
Give any MCP client (Claude Desktop, Cursor, …) live access to PlayerElo — player- and coach-level football Elo ratings, EAR, model market-value estimates, lineup-aware match predictions, value-bet signals, playing-style profiles and recruitment-fit — through the PlayerElo REST API.
Ask things like "What's Jude Bellingham's Elo and how has it trended this season?", "Which clubs are a good tactical + financial fit for player 129718?" or "Any value bets in the Premier League right now?" and the model answers from live data.
It's a thin client over the public API — no database, no model code. You bring an API key (free tier available); the server just makes authenticated calls.
Install & configure
You need a PlayerElo API key — get a free one at https://playerelo.football/api-access.
Claude Desktop
Add to claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):
{
"mcpServers": {
"playerelo": {
"command": "uvx",
"args": ["playerelo-mcp"],
"env": { "PLAYERELO_API_KEY": "pe_live_your_key_here" }
}
}
}
Restart Claude Desktop. (uvx comes with uv; or use
pipx run playerelo-mcp, or pip install playerelo-mcp and set "command": "playerelo-mcp".)
Cursor / other MCP clients
Same shape — command uvx, args ["playerelo-mcp"], and PLAYERELO_API_KEY in the env.
Tools
| Tool | What it does |
|---|---|
search_players / list_top_players |
find players by name / top by Elo |
get_player, get_player_history, get_player_value, get_player_style |
one player's rating, trajectory, model value, style |
get_player_opportunities |
reachable-club shortlist (Business tier) |
search_coaches, get_coach |
coaches by name / by id (unique to PlayerElo) |
search_clubs, get_club, get_club_squad_gaps |
clubs by name / by id / recruitment needs |
list_leagues, get_league_ranking |
competitions + Team-Elo tables |
get_predictions |
upcoming-match probabilities (refreshed ~every 10 min) |
get_value_bets |
value-bet signals; since=<last id> for just-new picks |
get_transfer_fit |
0–100 player→club fit score (Ultra tier) |
Every tool is available on every plan; plans differ only by monthly request volume. Some recruitment tools need a higher tier (noted above) — you'll get a clear message if your key can't reach one.
Config
| Env var | Default | |
|---|---|---|
PLAYERELO_API_KEY |
— | required; your key |
PLAYERELO_BASE_URL |
https://data-api.playerelo.football |
override the API base |
Develop
pip install -e ".[test]" # or: pip install -e . mcp httpx pytest
pytest tests/
Data & docs: https://playerelo.football/api-access · A LivingMeta project.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。