fpl-mcp
MCP server for the Fantasy Premier League API, enabling querying of players, teams, fixtures, and your FPL team through any MCP-compatible client.
README
<div align="center"> <h1><code>fpl-mcp</code></h1> <p>MCP server for the Fantasy Premier League API.</p> <p><i>Query players, teams, fixtures, and your FPL team through any MCP-compatible client.</i></p> </div>
Features
- Player Data — Search, filter, and compare players by stats, price, form, ownership
- Team Analysis — View Premier League team info and strength ratings
- Fixtures — Browse gameweek fixtures, team schedules, and FDR ratings
- Your Team — Fetch your FPL squad (via manager ID or API token)
- Differentials — Find low-ownership, high-form picks
- Auto-caching — Data cached locally with manual refresh option
Prerequisites
- Python 3.11+
- just (command runner)
Installation
git clone https://github.com/yourusername/fpl-mcp.git
cd fpl-mcp
just create-venv
just install
Configuration (optional)
Copy .env.example to .env to configure your manager ID:
cp .env.example .env
# Your FPL manager ID (from URL: fantasy.premierleague.com/entry/XXXXXX/...)
FPL_MANAGER_ID=123456
# Optional: API token for authenticated requests
FPL_API_TOKEN=
Client Setup
Claude Code
Add to ~/.claude/mcp_servers.json:
{
"fpl-mcp": {
"command": "/path/to/fpl-mcp/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/path/to/fpl-mcp",
"env": {
"FPL_MANAGER_ID": "123456"
}
}
}
Claude Desktop
Add to Claude Desktop config:
{
"mcpServers": {
"fpl-mcp": {
"command": "/path/to/fpl-mcp/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/path/to/fpl-mcp",
"env": {
"FPL_MANAGER_ID": "123456"
}
}
}
}
Cursor
Add to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"fpl-mcp": {
"command": "/path/to/fpl-mcp/.venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/path/to/fpl-mcp",
"env": {
"FPL_MANAGER_ID": "123456"
}
}
}
}
Usage
| Command | Description |
|---|---|
just info |
Show project info |
just run |
Run the MCP server |
just test |
Run tests |
just lint |
Lint with ruff |
just fmt |
Format with ruff |
Tools
Player Tools
| Tool | Description |
|---|---|
get_player |
Get player info by ID |
search_player |
Search players by name (partial match) |
filter_players |
Filter by position, team, price, form, points, availability |
get_top_players |
Rank by metric: points, form, ppg, xG, xA, value |
get_differentials |
Find low-ownership picks with high form |
compare_players |
Side-by-side comparison of multiple players |
Team Tools
| Tool | Description |
|---|---|
get_team |
Get team info by ID |
search_team |
Search teams by name |
get_all_teams |
List all 20 PL teams sorted by strength |
Fixture Tools
| Tool | Description |
|---|---|
get_gameweek_fixtures |
All fixtures for a gameweek |
get_team_fixtures |
Team's fixtures (optionally by gameweek) |
get_team_upcoming |
Next N fixtures with FDR ratings |
get_next_gameweeks |
Overview of upcoming gameweeks |
Manager Tools
| Tool | Description |
|---|---|
get_my_team |
Fetch your current FPL squad |
Utility
| Tool | Description |
|---|---|
refresh_cache |
Force refresh cached FPL data |
License
MIT
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。