Fantasy Premier League (FPL)

fpl-mcp

[Tests] [License: MIT]

An open-source MCP server for Fantasy Premier League that works with Claude, ChatGPT, Grok, Cursor, VS Code and any other MCP client. It pulls live data from the official FPL API and past seasons (2016-17 onward) from the vaastav dataset, predicts every player's points for the next five gameweeks, and recommends squads, transfers, captains and chips. Data lives in SQLite or Supabase.

Try it without installing anything:

• Remote URL: https://fpl-mcp-9tiv.onrender.com/mcp (claude.ai, ChatGPT, Grok, Cursor; see Connecting AI clients)
• npm: npx -y fpl-mcp-server for apps that run local servers (Claude Desktop, Cursor, VS Code)
• Smithery and the official MCP Registry (io.github.GilbertKamau/fpl-mcp)

The hosted server runs on a free plan, so the first request after a quiet spell can take a minute.

[An AI assistant answering 'Best midfielders under £7m for the next 3 gameweeks?' and 'Who are the best captains for GW7?' with fpl-mcp's predictions]

Example questions: "Who are the best midfielders under £7m for the next 3 gameweeks?", "Suggest transfers for team 1234567", "Should I play my Bench Boost this week?"

Setup

Requires Python 3.12+.

git clone https://github.com/GilbertKamau/fpl_mcp.git && cd fpl_mcppython -m venv .venv# Windows: .venv\Scripts\activate     macOS/Linux: source .venv/bin/activatepip install -e ".[supabase,dev]"fpl-sync all       # load data (~3 min to SQLite; ~15 min to a remote Supabase the first time)fpl-model all      # train the model and write predictions (~3-6 min the first time)

fpl-sync jobs:

fpl-model jobs: evaluate (test only), compare (feature sets side by side), train, predict, all (train + predict). Add --refresh-cache after re-loading history, so the local cache of past seasons is rebuilt.

Database

SQLite at data/fpl.db by default. To use Supabase, copy .env.example to .env and paste your Supabase Session pooler connection string as DATABASE_URL (the direct db.<ref>.supabase.co host is IPv6-only). Special characters in the password are encoded automatically. Tables are created automatically.

Data quirks: 2019-20 gameweeks run to 47 (the COVID restart was numbered 39-47); 2024-25 includes AM (assistant manager) rows, which the model ignores; xG/xA exist from 2022-23 onward.

data/ (SQLite backup, cache, logs), models/ and .env are git-ignored, and a local pre-commit hook refuses to commit them.

Prediction model

LightGBM predicts each player's points per fixture from information available before kick-off:

• Form: rolling averages over the last 1, 3, 6, 12 and 38 matches (points, minutes, starts, xG, xA, bonus, BPS, ICT, defensive contributions...)
• Market: ownership and net transfers that gameweek, as percentiles (the crowd's read on fitness and form)
• Context: price, position, home/away, days since the last match
• Team strength: both clubs' recent goals and xG for and against

A gameweek's expected points is the sum over its fixtures, so double gameweeks count twice. Injury and suspension news scales the next gameweek's prediction by FPL's chance of playing. The trained model is stored in the database, so any machine can make predictions with it.

Testing on past seasons. Walk-forward: for each of the last three complete seasons, the model is trained only on earlier seasons and predicts every fixture. The baseline is the player's average points over their last 6 matches.

That is 7.5% better than the baseline overall. Adding last-match form, season-long form and the market features improved the average MAE from 0.982 to 0.958 and was better in every test season (fpl-model compare reruns this). A retrained model is only used if it beats the baseline and is no worse than the current model.

Past-season tests have no injury news (there's no historical record of it), so they understate live accuracy. They also can't fairly be compared with FPL's own expected points: the historical xP column includes injury news, and its 2025-26 values are on a different scale.

Live tracking. Every prediction is archived. After each gameweek, the prediction made before the deadline is scored against actual points, next to two benchmarks recorded at the same moment: the 6-match baseline and FPL's own expected points (ep_next). It also compares what each method's top 20 players actually scored. model_report shows the running results.

FPL points are very noisy (a 2-pointer and a 15-pointer can come from the same performance), so treat predictions as estimates.

Optimizer

Integer programs solved with HiGHS (via PuLP) that follow FPL rules: 2 GKP / 5 DEF / 5 MID / 3 FWD, max 3 per club, a valid formation, the budget, and −4 per transfer beyond the free ones. Points for later gameweeks are discounted (×0.85 per week) because predictions further out are less reliable.

For a manager's team it uses public endpoints only (no login). Selling prices are estimated from the manager's transfer history (FPL keeps half of any price rise), and free transfers from their gameweek history (up to 5 banked, kept through Wildcard and Free Hit weeks). Transfers made since the last deadline aren't public yet, so they aren't included.

MCP tools

Connecting AI clients

There are two ways to run the server:

• Local (stdio): your AI app starts the server on your computer. Works with Claude Code, Claude Desktop, Cursor and VS Code. Nothing is exposed to the internet.
• Remote (HTTP): you host the server at a public HTTPS URL (see Deploying). Required for claude.ai, ChatGPT and Grok, which can't start programs on your computer.

In the examples, /path/to/fpl_mcp/.venv/bin/python is the Python inside your virtual environment (Windows: C:\path\to\fpl_mcp\.venv\Scripts\python.exe), and https://your-server.example.com/mcp is your deployed URL.

Claude Code

claude mcp add fpl -- /path/to/fpl_mcp/.venv/bin/python -m fpl_mcp.server        # localclaude mcp add --transport http fpl https://your-server.example.com/mcp          # remote

Claude Desktop

Local: Settings > Developer > Edit Config, then add to claude_desktop_config.json:

{  "mcpServers": {    "fpl": { "command": "/path/to/fpl_mcp/.venv/bin/python", "args": ["-m", "fpl_mcp.server"] }  }}

Remote: use Settings > Connectors > Add custom connector (same as claude.ai below).

claude.ai

Settings > Connectors > Add custom connector, and paste https://your-server.example.com/mcp. Available on paid plans; on Team/Enterprise an owner adds it for the organization. claude.ai connects to servers without a login or with OAuth, so leave MCP_AUTH_TOKEN unset.

ChatGPT

Turn on Developer mode (Settings > Apps & Connectors > Advanced), create a connector with the URL https://your-server.example.com/mcp and authentication None, then pick it from the tools menu in a chat. Plan availability varies, so check OpenAI's current docs. Like claude.ai, it can't send a fixed token, so leave MCP_AUTH_TOKEN unset.

Grok (xAI API)

Grok connects to remote MCP servers through the xAI API:

from xai_sdk import Clientfrom xai_sdk.chat import userfrom xai_sdk.tools import mcp
client = Client()  # reads XAI_API_KEYchat = client.chat.create(    model="grok-4.7",    tools=[mcp(server_url="https://your-server.example.com/mcp", server_label="fpl")],)chat.append(user("Who should I captain in gameweek 7?"))print(chat.sample().content)

Or with the Responses API, add this to tools:

{ "type": "mcp", "server_url": "https://your-server.example.com/mcp", "server_label": "fpl" }

If you set MCP_AUTH_TOKEN, also pass "authorization": "<token>".

Cursor

Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):

{  "mcpServers": {    "fpl": { "command": "/path/to/fpl_mcp/.venv/bin/python", "args": ["-m", "fpl_mcp.server"] }  }}

Remote: "fpl": { "url": "https://your-server.example.com/mcp" }, plus "headers": { "Authorization": "Bearer <token>" } if you set a token.

VS Code (GitHub Copilot agent mode)

.vscode/mcp.json:

{  "servers": {    "fpl": { "type": "stdio", "command": "/path/to/fpl_mcp/.venv/bin/python", "args": ["-m", "fpl_mcp.server"] }  }}

Remote: "fpl": { "type": "http", "url": "https://your-server.example.com/mcp" }.

Anything else

Any MCP client that supports stdio or Streamable HTTP works. To try the server interactively: npx @modelcontextprotocol/inspector /path/to/fpl_mcp/.venv/bin/python -m fpl_mcp.server.

Deploying

The hosted server only reads the database. Data, training and predictions run on your own machine (or any scheduled job) with fpl-sync weekly, and the hosted server picks up new predictions within 10 minutes. You therefore need a database both can reach, such as Supabase.

1. Create a read-only database user for the public server: run scripts/supabase_readonly_role.sql in Supabase's SQL editor.

2. Deploy. On Render: New > Blueprint, pick your fork of this repo, and render.yaml sets it up. Elsewhere (Fly.io, Railway, Google Cloud Run, a VPS), use the Dockerfile.

3. Set environment variables:

   Variable	Required	Purpose
   DATABASE_URL	yes	Supabase Session pooler URI for the read-only user
   MCP_AUTH_TOKEN	no	If set, every request needs Authorization: Bearer <token>. Grok, Cursor and VS Code can send it; claude.ai and ChatGPT can't
   FPL_MCP_ALLOW_REFRESH	no	1 exposes the refresh_data tool (off by default when hosted)
   PORT	no	Set by most hosts automatically; defaults to 8000

4. Your MCP URL is https://<your-app>/mcp. https://<your-app>/health should return {"status":"ok"}.

To run the HTTP server locally: fpl-mcp --http (serves http://127.0.0.1:8000/mcp).

Without a token, anyone with the URL can call the tools. The data is public FPL data and the server is read-only, but if the URL gets shared widely, set a token or put it behind your host's access controls.

Scheduled updates

GitHub Actions keeps the shared database fresh:

Run it by hand from the Actions tab (Scheduled update > Run workflow). It needs a repository secret DATABASE_URL with write access, and only runs in the main repository, not in forks. To run your own copy, add the secret to your fork and change the if: line in the workflow.

Without GitHub Actions, run fpl-sync weekly (or fpl-sync live + fpl-model predict) from cron or Windows Task Scheduler; scripts\update.ps1 wraps both modes for Windows and logs to data\logs.

Tests

.venv\Scripts\python -m pytest

Roadmap

1. Data pipeline (FPL API + vaastav → SQLite/Supabase)
2. Read-only MCP tools
3. Points prediction: LightGBM with walk-forward validation against a rolling-average baseline (plus live tracking against FPL's own expected points)
4. Optimizer: best squad, transfers, captain, chip advice
5. Scheduled updates (sync → retrain → predict) on GitHub Actions
6. HTTP hosting for claude.ai, ChatGPT, Grok and other remote clients
7. Optional: apply changes to your FPL team (preview-only by default)

Contributing

Issues and pull requests are welcome. Please run pytest before opening a PR, and never commit .env, data/ or models/. By submitting a contribution you agree that it is licensed under this project's MIT License.

Licence

Copyright (c) 2026 Gilbert Kamau. Released under the MIT License: you may use, copy, modify and distribute the code, including commercially, as long as you keep the copyright and licence notice. Third-party software and data are listed in THIRD_PARTY_NOTICES.md.

Credits and disclaimer

Historical data comes from vaastav/Fantasy-Premier-League (code under the MIT License); live data from the public FPL API. Fantasy Premier League data is the property of the Premier League; the MIT License covers this project's code only, not the data. This project is not affiliated with or endorsed by the Premier League or Fantasy Premier League. Use the FPL API responsibly, and treat predictions as estimates, not guarantees.