FPL Advisor MCP Server

FPL Advisor MCP Server

An MCP server that provides Fantasy Premier League advice, including transfer suggestions, captain recommendations, and differential player discovery.

Category
访问服务器

README

FPL Advisor MCP Server

A Model Context Protocol (MCP) server that gives Fantasy Premier League advice. Built with FastMCP.

Tools

Tool Description
recommend_transfer(team_json) Suggest transfer targets based on form and value
recommend_captain(team_json) Pick the best captain from your squad
find_differentials(max_price) Find low-ownership players under a price ceiling

team_json is a JSON array of player names, e.g. '["Erling Haaland", "Mohamed Salah"]'.

1. Run Locally

# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh

# Run with MCP Inspector (opens a browser UI to test tools)
uv run mcp dev server.py

# Or run the server directly
uv run python server.py

2. Connect to Claude Desktop / Cursor

Add this to your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "fpl-advisor": {
      "command": "uv",
      "args": ["run", "--directory", "/ABSOLUTE/PATH/TO/fpl-advisor-mcp", "python", "server.py"]
    }
  }
}

Replace /ABSOLUTE/PATH/TO/fpl-advisor-mcp with the actual path, then restart Claude Desktop.

3. Connect to Claude Code

Add the MCP server to your project settings:

claude mcp add fpl-advisor -- uv run --directory /ABSOLUTE/PATH/TO/fpl-advisor-mcp python server.py

Sample prompts to try

Once connected, try these prompts in Claude Code:

Who should I captain this week? My team has Haaland, Salah, Saka, Palmer, and Watkins.
I have £7m to spend — find me a differential pick that no one else owns.
Suggest a transfer for my team: Haaland, Salah, Trent, Saka, Watkins.
Who gives me the best value for money?
Compare Cole Palmer vs Bukayo Saka — who's the better FPL asset right now?
Build me a front three under £30m using the best form-to-price ratio.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选