Fantasy Premier League

Fantasy Premier League MCP

An MCP server for Fantasy Premier League that works with any MCP-capable agent — read your squad and stats, rank players, work out differentials, and make changes to your team. It is published in the official MCP Registry and works over either stdio or remote streamable HTTP.

This project is packaged on PyPI as fantasy-premier-league-mcp, rather than fpl-mcp, which is already owned by an unrelated project.

Install

Install it with uv (recommended):

uv tool install fantasy-premier-league-mcp

Or run it without installing:

uvx fantasy-premier-league-mcp

fpl_login also needs a local Chromium installation. Install it once with:

uvx --from playwright playwright install chromium

For development, create a virtual environment and install the project:

uv sync --group dev

uv run playwright install chromium

Releasing

Releases are published by GitHub Actions when a matching version tag is pushed. The workflow tests and builds the package, publishes it to PyPI using Trusted Publishing, then publishes the matching server.json to the official MCP Registry. No PyPI API token is stored in GitHub.

Before the first release, configure a PyPI pending Trusted Publisher with:

• owner: anubabajide
• repository: fpl-mcp
• workflow: release.yml
• environment: pypi
• PyPI project: fantasy-premier-league-mcp

Create a protected GitHub environment named pypi (for example, require manual approval). Once that one-time setup is complete, publish a prepared version with:

git tag v0.3.2

git push origin v0.3.2

Playwright drives the one-off browser sign-in described under Authentication.

Connect it to your agent

Any MCP-capable client can use this server. It speaks MCP over stdio by default, and can also run as a remote streamable-HTTP connector for agents that support remote MCP servers.

Local stdio (recommended)

Point your agent at uvx:

{

"mcpServers": { "fpl": { "command": "uvx", "args": ["fantasy-premier-league-mcp"] } } }

Use that block in your client's MCP configuration — many clients accept a .mcp.json/.cursor/mcp.json file or offer a settings screen. Some clients call the top-level key servers instead of mcpServers; the fpl entry is the same. For a checked-out copy, point command at the project's Python and run python -m fpl_mcp.

Nothing is exposed off the machine in stdio mode. This is the safest option.

Remote HTTP

Agents that connect to remote MCP servers over HTTPS can use the built-in HTTP transport:

export FPL_MCP_SHARED_SECRET="$(python -c 'import secrets; print(secrets.token_urlsafe(32))')"

python -m fpl_mcp --http

Then put an HTTPS tunnel in front of it (for example cloudflared tunnel --url http://localhost:8000) and give the agent the resulting https://…/mcp URL as a custom connector.

HTTP mode refuses to start without `FPL_MCP_SHARED_SECRET` (16+ characters). These tools can transfer players and rewrite your lineup, so an open endpoint would let anyone who found the URL edit your team. Every request must carry Authorization: Bearer ; anything else gets a 401. Your machine has to be running for the connector to work.

MCP Bundle

For apps that install local MCP servers as bundles, fpl.mcpb is a zip containing the server, its dependencies and a bundled Python interpreter, plus a manifest.json. Install it through the app's extension UI. See the MCP Bundle setup notes for build, update and Chromium details.

Registry discovery

The server is listed in the official MCP Registry as io.github.anubabajide/fpl, so registry-aware clients can find and install it directly.

Authentication

Everything read-only works with no login at all. Only the three write tools (fpl_set_lineup, fpl_set_captain, fpl_make_transfers) need a session.

Sign in once: ask your agent to run fpl_login. It opens FPL's own sign-in page in a browser window on the machine running the server and returns promptly:

1. Sign in in that browser window.
2. The server catches the redirect FPL sends back, exchanges the authorization code, and saves the resulting session automatically — there is no second fpl_login call.

The sign-in runs as an independent background task, so it keeps going even if the client gives up on the first call — your progress in the window is never thrown away. You sign in yourself; this server never sees your password. The session is kept as a refresh token in ~/.fpl-mcp/credentials.json, readable only by you, and access tokens are renewed with a single HTTPS request. No browser is involved after sign-in. You should not need to think about tokens again until the session itself lapses, at which point any write tool will tell you to run fpl_login again. fpl_auth_status can check whether a browser sign-in has finished.

If no browser window can be opened, fpl_login returns status awaiting_redirect_url with a sign_in_url. Open that link in any browser; after signing in, paste the address you land on back into fpl_login as redirect_url.

fpl_logout forgets the session and revokes it at FPL. fpl_auth_status reports the current state.

Why not just store an email and password?

Because FPL's identity provider refuses that exchange. The site's OAuth client (bfcbaf69-aade-4c1b-8f00-c1cb8a193030, read from the FPL app bundle) is configured without the password grant:

POST https://account.premierleague.com/as/token

grant_type=password -> 400 unsupported_grant_type: "Invalid grant type: password"

The supported flow is authorization-code + PKCE in a browser, and account.premierleague.com rejects non-browser HTTP clients outright. So a real browser has to be involved somewhere. Doing it this way means the login is performed by you, on FPL's own page in a genuine browser window, and no FPL credentials are ever stored, read, or handled by this server. The authorization code is redeemed with a PKCE verifier held only in memory, and what is saved afterwards is a refresh token — not a password and not a browser profile.

If the login ever presents two-factor or a bot check, you complete it in that window like any other sign-in. Nothing is bypassed.

Fallback

fpl_set_token still accepts a bearer token pasted by hand from DevTools, for machines where launching a browser is not an option. Such a token lasts about an hour, cannot renew itself, and is retained only until the server stops.

Tools

Setup

Your team

Player research

Bulk export (for your own modelling)

These return whole datasets rather than a ranked top-N, so a client can run its own optimiser. CSV is the default: the same data as JSON costs roughly five times the tokens.

The default player export is compact — about 22 columns — so it fits in a tool result. fields="standard" restores the broad optimiser set (62 columns), and fields="all" gives every raw column (112) with a size warning. Narrow further with ids, position, team, min_minutes or max_price, or page with offset/limit; the response carries has_more and next_offset.

Join fpl_export_fixtures to the player export on team_id to build per-player, per-gameweek projections. Blanks and doubles fall out of the shape: no row for a gameweek means a blank, two rows mean a double.

Team news and lineups

Managers come from the Premier League's own Pulse backend, joined to FPL on the pulse_id field FPL already ships. It is undocumented and unversioned, so when it does not answer the manager reads unknown rather than failing the call. Managers are not an FPL asset this season, so a change matters indirectly — rotation, set-piece duty, formation — not as points.

Signings and departures need no extra source: FPL's team_join_date is a real transfer feed, and its news text carries departures and loans verbatim.

Predicted lineups do not exist as data anywhere — they are editorial judgement. fpl_predicted_lineups therefore returns one of two things:

• source: "confirmed" — the real team list, once the league publishes it about an hour before kickoff;
• source: "predicted" — a heuristic derived here, ranked on recent starts, minutes per appearance, availability, set-piece duty and price. Every pick carries its score_breakdown so you can disagree with the weighting.

The season prior is split into rate and volume, because total minutes alone conflates "was injured" with "is not a starter". Odegaard started only 16 games last season but averaged 85 minutes in them — nearly identical to Rice's 88 — so scoring on totals alone dropped a nailed-on captain out of the XI. Minutes-per-start now carries more weight than starts, since fitness returns and a squad role does not.

Recent signings are scored on fee instead, since a July arrival has no club minutes and one from abroad has none recorded anywhere. Those rows are flagged new_signing. Because they score on absent evidence rather than on merit, any who miss the XI are listed separately under new_signings_not_predicted — left to the ranking alone they would fall off the bottom and read as "not considered", when the truth is "cannot be judged".

Nothing here can see a new manager's preferences, pre-season friendlies, or a press conference.

Differentials

Changing your team (all preview first)

How differentials work

fpl_differentials answers the question in both directions, which is what you asked for:

• `my_differentials` — high performers *you* own that few rivals do. When these return points, you gain ground on ever