FPL Intelligence
AI-powered Fantasy Premier League assistant — scored captain picks, transfer suggestions, differentials, fixture outlook, price predictions, live points, and a full manager hub that auto-detects your squad, bank balance, and free transfers.
README
FPL Intelligence — MCP Server
AI-powered Fantasy Premier League assistant for Claude Desktop. Get personalized captain picks, transfer suggestions, differentials, fixture analysis, price predictions, and live points — all from real FPL data.
Quick Start
1. Install:
pip install fpl-intelligence
2. Add to Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"fpl": {
"command": "fpl-intelligence"
}
}
}
3. Restart Claude Desktop and ask:
"Analyze FPL team YOUR_TEAM_ID and give me your full recommendation."
That's it. Bank balance, free transfers, and chips are all auto-detected — just provide your team ID.
Install from Source
git clone https://github.com/dohyung1/x402-fpl-api.git
cd x402-fpl-api
uv sync
{
"mcpServers": {
"fpl": {
"command": "uv",
"args": ["run", "--directory", "/path/to/x402-fpl-api", "mcp_server.py"]
}
}
}
Find Your FPL Team ID
Go to the FPL website, click "Points", and look at the URL:
https://fantasy.premierleague.com/entry/YOUR_TEAM_ID/event/<gw>
What Can It Do?
| Tool | What it does |
|---|---|
fpl_manager_hub |
Start here. Full personalized analysis — captain, transfers, differentials, fixtures, price risks |
captain_pick |
Top 5 captain recommendations scored by xG, form, fixtures, and ICT index |
transfer_suggestions |
Transfer in/out recommendations based on your squad and budget |
player_comparison |
Head-to-head compare 2-4 players (e.g. "Salah vs Palmer vs Saka") |
is_hit_worth_it |
Should you take a -4 hit? Projects points over N gameweeks to decide |
chip_strategy |
When to use your remaining chips — optimal GW for each based on fixtures |
differential_finder |
Underowned players outperforming their ownership % |
fixture_outlook |
Teams ranked by upcoming fixture difficulty + best players to target |
price_predictions |
Players likely to rise or fall in price tonight |
live_points |
Live score, projected bonus, and auto-sub scenarios |
squad_scout |
Deep scout using FPL's hidden data — expected points, blank GW warnings, set piece duties, suspension risks |
Example Prompts
Try these in Claude Desktop:
- "Analyze FPL team 5456980 and give me your full recommendation"
- "Who should I captain this gameweek?"
- "Compare Salah, Palmer, and Saka"
- "Is it worth taking a -4 hit to bring in Haaland?"
- "When should I use my bench boost?"
- "Find me some differentials under 5% ownership"
- "Which teams have the easiest fixtures for the next 6 weeks?"
How It Works
FPL Intelligence connects directly to the FPL API — the same free, public data source used by the FPL website. All data is real-time. The server runs locally on your machine and communicates with Claude Desktop via the Model Context Protocol (MCP).
No API keys. No accounts. No data leaves your machine except FPL API calls.
Contributing
See CONTRIBUTING.md for development setup and guidelines.
License
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.