fpl-context-mcp

An MCP server that gives any MCP-capable AI agent Fantasy Premier League (FPL) data. It works with zero setup: install and run it, and your assistant can read the current gameweek, fixtures with difficulty ratings, player stats, any manager's squad and chips, and live injury and suspension flags, all straight from the public FPL API. Optionally, point it at your own PostgreSQL database to also query historical stats with SQL. It runs locally in Claude Desktop, Claude Code, Cursor, VS Code Copilot, Windsurf, Gemini CLI and Codex; ChatGPT and other clients that only accept a URL can connect when you host it over HTTP.

Live tools: no database, no configuration

Optional: your own history database

An ingestion job keeps that database populated and current:

query_historical_stats only reads what is already in your PostgreSQL database. It starts out empty: you must run the ingestion job once to seed it, and then keep running it on a recurring schedule forever, or its answers will silently go stale. See Keeping data fresh (ongoing). The live tools need none of this; they always return FPL's current data.

Prompts and resources. Clients that support MCP prompts show captain_pick, transfer_plan and chip_timing as slash commands (for example /mcp__fpl-context__captain_pick in Claude Code); each walks the model through the right tools. Two resources, fpl://schema (the database schema; only listed when a database is configured) and fpl://glossary (status codes, FDR, which tool answers what), can be attached as context. See Prompts and resources.

Contents

• Quickstart
• Prerequisites
• Installation
• Configuration
• Provisioning your database
• Seeding data (required before first use)
• Keeping data fresh (ongoing)
• Registering with Claude Desktop
• Other AI clients (local)
• Remote access over HTTP (ChatGPT and other URL-only clients)
• Running the server standalone
• Verifying connectivity (--check)
• Dry-run mode
• MCP tools reference
• Prompts and resources
• Database schema
• Running tests
• Data sources and disclaimer
• License

Quickstart

Fastest path: live tools, no database

uvx fpl-context-mcp

Register it with your client (Claude Desktop config: {"mcpServers": {"fpl-context": {"command": "uvx", "args": ["fpl-context-mcp"]}}}) and ask "who should I captain this week?" or "show Arsenal's next five fixtures". That's it. Everything below is only needed for the optional SQL history tool.

Full path: add the history database

The full path from zero to a working query_historical_stats tool, in order. Each step links to details further down.

1. Install: pip install fpl-context-mcp — see Installation.
2. Provision storage: a PostgreSQL database. Run db/schema.sql against a fresh Postgres database — see Provisioning your database.
3. Configure: copy .env.example to .env and fill in your DATABASE_URL and DATABASE_ETL_URL — see Configuration.
4. Verify connectivity: fpl-context-mcp --check — confirms every credential works before you go further.
5. Seed data: run the match ingestion command, then the one-time history backfill, so there's actually something to query — see Seeding data.
6. Schedule ongoing ingestion: set up cron (or equivalent) to keep re-running the match ingestion command (not the backfill) indefinitely — see Keeping data fresh. Skipping this is the #1 cause of "the tool returns nothing" reports.
7. Connect your AI client: Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI or Codex, or — for ChatGPT and other clients that only accept a URL — run it over HTTP.

Prerequisites

The live tools need only Python and outbound HTTPS to fantasy.premierleague.com. If you want the SQL tool, you provision the database yourself: see the next sections. Free tiers (Neon, Supabase, etc.) are plenty: the data is a few MB per season.

Installation

From PyPI (recommended)

pip install fpl-context-mcp

This installs three CLI commands: fpl-context-mcp (the MCP server), fpl-context-ingest-match (the recurring ingestion job), and fpl-context-backfill-history (a one-time job for past seasons) — see Seeding data.

With uv

git clone https://github.com/sbanthia92/fpl-context-mcp
cd fpl-context-mcp
uv sync

With pip (from source)

git clone https://github.com/sbanthia92/fpl-context-mcp
cd fpl-context-mcp
pip install -e ".[dev]"

As a dependency of another project

fpl-context-mcp @ git+https://github.com/sbanthia92/fpl-context-mcp.git

Configuration

The server reads all secrets from environment variables. Copy .env.example to .env in your working directory (it's gitignored) and fill in your own values:

# PostgreSQL — read-only connection for the query_historical_stats tool
DATABASE_URL=postgresql://fpl_readonly:password@localhost:5432/fpl

# PostgreSQL — read/write connection for the ingest_match_data job
# Falls back to DATABASE_URL if not set
DATABASE_ETL_URL=postgresql://fpl_etl:password@localhost:5432/fpl

# HTTP transport only (fpl-context-mcp --transport http). Requests to /mcp must
# send "Authorization: Bearer <token>". Leave empty only when bound to localhost.
# MCP_AUTH_TOKEN=

Which variables does each component need?

Run fpl-context-mcp --check any time to confirm all of the above are set correctly and reachable — see Verifying connectivity.

Provisioning your database

createdb fpl   # or whatever database name you'll use in DATABASE_URL
psql fpl -f db/schema.sql

db/schema.sql creates the six tables query_historical_stats expects (seasons, teams, gameweeks, players, fixtures, gw_player_stats) and includes example CREATE ROLE statements for the read-only and read/write roles referenced in .env.example. It's a starting schema, not a full migration tool — adjust types/constraints as needed.

Serving the database to other people? Use db/hosted_role.sql instead of the example role: it limits the role to these six tables and adds a connection cap and server-side timeouts.

The tables start completely empty. Continue to Seeding data.

Seeding data (required before first use)

The ingestion jobs are plain commands you run directly — nothing runs automatically on pip install or on MCP server startup.

# If installed from PyPI
fpl-context-ingest-match
fpl-context-backfill-history   # one-time: past seasons (see below)

# If running from source
python -m jobs.ingest_match_data
python -m jobs.backfill_history

Run these once, right after configuring your .env, before registering the server with Claude Desktop. Run fpl-context-ingest-match before the backfill. Until you do, query_historical_stats returns Query returned no results. for any query, since the tables are empty.

ingest_match_data loads the current season: every team, gameweek, player and fixture, plus per-player stats for matches already played (the first run can take several minutes mid-season, since it fetches stats player by player). Later runs are quick — see What each run updates.

fpl-context-backfill-history adds past seasons (as far back as FPL has them, about 20). It reads FPL's per-player season history and writes one row per player per season into players. It's safe to re-run and only needs to run once, since past seasons don't change. Know its limits:

• It holds season totals only — points, minutes, goals, assists, clean sheets, cards, bonus. FPL doesn't serve past fixtures, teams or match-by-match stats, so those tables only ever contain the current season.
• Past-season rows have team_fpl_id set to NULL (FPL doesn't say which team a player was on), and fpl_id is the player's current FPL id.
• It only covers players in FPL's current player list. Anyone who has left the league (or retired) has no history here, so a question about a departed player returns nothing, and league-wide or team-wide totals for a past season are incomplete. Per-player questions about current players are reliable.

Keeping data fresh (ongoing)

This is not a one-time step. Fixtures change weekly, player stats update after every match, and injury/availability news changes daily. If you seed once and never run the job again, a query a month later will hit a database that's missing every result, stat and injury update since your last run.

You need something to invoke fpl-context-ingest-match on a recurring schedule, indefinitely, for as long as the MCP server is in use. (The backfill is not part of this — run it once.) Pick whichever fits your setup:

What each run updates

Runs are on a clock, not tied to gameweeks — nothing triggers when a match ends. A result shows up in your database at the first run after FPL marks the fixture finished.

Run more often on matchdays if you want results sooner — each run takes a minute or two, and steady-state runs make very few requests to FPL.

Option A — cron (simplest, any Linux/macOS host)

# Match data: twice daily during the season (06:00 + 22:00 UTC)
0 6,22 * * * /path/to/venv/bin/fpl-context-ingest-match >> /var/log/fpl-context-ingest-match.log 2>&1

Adjust the match-data cadence to the calendar:

Option B — GitHub Actions in your own private repo (free, no server needed)

Best if you don't have a machine that's always on. You don't fork this project — you create a tiny repo of your own with one file that installs the package from PyPI and runs the ingestion command on a schedule.

1. Create a new private GitHub repository (any name).

2. Add this file as .github/workflows/ingest.yml:

   name: Ingest sports data
   
   on:
     schedule:
       - cron: "0 6,22 * * *" # twice daily, UTC
     workflow_dispatch: {} # lets you run it by hand from the Actions tab
   
   jobs:
     ingest:
       runs-on: ubuntu-latest
       steps:
         - uses: actions/setup-python@v5
           with:
             python-version: "3.11"
         - run: pip install fpl-context-mcp
         - name: Ingest match data
           run: fpl-context-ingest-match
           env:
             DATABASE_URL: ${{ secrets.DATABASE_URL }}
             DATABASE_ETL_URL: ${{ secrets.DATABASE_ETL_URL }}
   

3. In that repo: Settings → Secrets and variables → Actions → New repository secret, and add DATABASE_URL and DATABASE_ETL_URL.

4. Open the Actions tab, pick "Ingest sports data", and click Run workflow once to seed your data. From then on it runs by itself on the schedule.

Notes:

• A failed run turns red and GitHub emails you (missing credentials, a database that's unreachable, an API outage), so you'll know if data stops flowing.
• Updates: pip install fpl-context-mcp grabs the latest release on every run, so fixes arrive automatically. Pin a version (fpl-context-mcp==0.3.0) if you'd rather upgrade on purpose.
• Cost: each run takes about a minute or two, so a twice-daily schedule stays well inside GitHub's free monthly minutes for private repos.
• Why private: GitHub automatically pauses scheduled workflows in public repos after 60 days without a commit. Private repos aren't paused.

Option C — any other scheduler

Managed cron (Render, Railway, Fly.io machines, GCP Cloud Scheduler + Cloud Run Jobs, AWS EventBridge + Lambda/Fargate, systemd timers, Airflow, Dagster, etc.) all work the same way — point it at fpl-context-ingest-match (or python -m jobs.ingest_match_data) with the cadence table above and the environment variables from Configuration.

Whichever option you pick, re-run fpl-context-mcp --check afterward to confirm the scheduled job's credentials actually work in that environment — a job that silently fails every night is worse than no job, since nothing tells you the data's gone stale.

Registering with Claude Desktop

Add the server to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).

Zero setup, live tools only (no database)

{
  "mcpServers": {
    "fpl-context": {
      "command": "uvx",
      "args": ["fpl-context-mcp"]
    }
  }
}

If installed from PyPI, with the history database

{
  "mcpServers": {
    "fpl-context": {
      "command": "fpl-context-mcp",
      "env": {
        "DATABASE_URL": "postgresql://fpl_readonly:password@localhost:5432/fpl"
      }
    }
  }
}

If running from source

{
  "mcpServers": {
    "fpl-context": {
      "command": "python",
      "args": ["/absolute/path/to/fpl-context-mcp/server.py"],
      "env": {
        "DATABASE_URL": "postgresql://fpl_readonly:password@localhost:5432/fpl"
      }
    }
  }
}

Tip: If you use uv, replace "python" with "uv" and prepend "run" to args:

"command": "uv",
"args": ["run", "/absolute/path/to/fpl-context-mcp/server.py"]

Restart Claude Desktop. You should see fpl-context appear in the tools panel. If the tool returns nothing useful, re-check Seeding data and Keeping data fresh before assuming the server itself is broken.

Other AI clients (local)

Any client that can launch a local MCP server (stdio) works the same way: run the fpl-context-mcp command (add DATABASE_URL to its environment only if you want the SQL history tool). Swap in your own values below.

Claude Code

claude mcp add fpl-context -e DATABASE_URL=postgresql://fpl_readonly:password@localhost:5432/fpl -- fpl-context-mcp

Cursor (~/.cursor/mcp.json), Windsurf (~/.codeium/windsurf/mcp_config.json) and Gemini CLI (~/.gemini/settings.json) all use the same mcpServers shape as Claude Desktop:

{
  "mcpServers": {
    "fpl-context": {
      "command": "fpl-context-mcp",
      "env": {
        "DATABASE_URL": "postgresql://fpl_readonly:password@localhost:5432/fpl"
      }
    }
  }
}

VS Code (Copilot agent mode) — .vscode/mcp.json in your workspace:

{
  "servers": {
    "fpl-context": {
      "type": "stdio",
      "command": "fpl-context-mcp",
      "env": {
        "DATABASE_URL": "postgresql://fpl_readonly:password@localhost:5432/fpl"
      }
    }
  }
}

OpenAI Codex CLI — ~/.codex/config.toml:

[mcp_servers.fpl-context]
command = "fpl-context-mcp"
env = { DATABASE_URL = "postgresql://fpl_readonly:password@localhost:5432/fpl" }

Without installing first — if you have uv, use "command": "uvx" with "args": ["fpl-context-mcp"] in any of the configs above.

Your own agent code — the MCP SDKs (Python, TypeScript) and agent frameworks such as the OpenAI Agents SDK can launch fpl-context-mcp as a stdio server, or connect to it over HTTP as below.

Remote access over HTTP (ChatGPT and other URL-only clients)

Some clients can't launch a local process — they only accept a server URL. That includes ChatGPT (Settings → Apps & Connectors → Advanced → Developer mode → create a connector) and custom connectors on claude.ai. For these, run the server with the streamable HTTP transport on a machine with a public HTTPS address:

MCP_AUTH_TOKEN=some-long-random-string \
fpl-context-mcp --transport http --host 0.0.0.0 --port 8000

• The MCP endpoint is https://<your-host>/mcp; GET /health returns ok for load-balancer and platform health checks.
• --transport, --host and --port can also be set with MCP_TRANSPORT, MCP_HOST and MCP_PORT (or the PORT variable that Render, Cloud Run, Heroku and Fly set).
• The server listens on plain HTTP. Put it behind something that terminates TLS — any of those platforms does, or cloudflared tunnel / ngrok for a quick test from your own machine.
• The default bind address is 127.0.0.1, so nothing is exposed until you pass --host 0.0.0.0.

Authentication. With MCP_AUTH_TOKEN set, every request to /mcp must send Authorization: Bearer <token>; others get HTTP 401. Clients that let you set headers can use it — for example Claude Code:

claude mcp add --transport http fpl-context https://your-host/mcp --header "Authorization: Bearer some-long-random-string"

and the OpenAI Agents SDK / Responses API MCP tool (headers={"Authorization": "Bearer ..."}).

Several keys. MCP_AUTH_TOKEN accepts a comma-separated list (key-alice,key-bob). Each user can have their own key, and removing one from the list revokes it without touching the others. Rate limits are applied per key.

Rate limiting and load. Set these before exposing a server publicly:

ChatGPT and claude.ai connectors only support OAuth or no authentication — not a static bearer token. To use them you currently have to leave MCP_AUTH_TOKEN unset (the endpoint is then open to anyone who finds the URL) or put an OAuth-capable proxy in front. If you run it open, understand what that exposes: anyone can run read-only SELECTs against the database behind DATABASE_URL (10-second timeout, 100-row cap). Only do that with the dedicated fpl_readonly role on a database that holds nothing but FPL data. The server logs a warning at startup when it's bound to a non-local address without a token.

Running a public endpoint? See the hosting guide: database role, container, proxy setup, auth modes, and a canary that checks the endpoint and its data freshness every 15 minutes.

Container. A Dockerfile is included: docker build -t fpl-context-mcp ., then run it with DATABASE_URL (and MCP_AUTH_TOKEN) set. It runs as a non-root user, listens on $MCP_PORT / $PORT / 8000, defaults to a rate limit of 120 requests a minute, and has a health check on /health.

Where the data comes from. A hosted server reads your database, exactly like a local one — you still need the ingestion job on a schedule (Keeping data fresh). And because you're now serving results to other people, see Data sources and disclaimer.

Running the server standalone

# If installed from PyPI
fpl-context-mcp

# If running from source
python server.py

By default the server communicates over stdio — it is designed to be launched by an MCP client, and running it directly is mainly useful for smoke-testing startup and environment variable loading. To run it as a persistent network service instead, use --transport http (see Remote access over HTTP).

Verifying connectivity (--check)

Before registering the server with a client — and any time something seems off — verify that your environment variables are correct and all backends are reachable:

# If installed from PyPI
fpl-context-mcp --check

# If running from source
python server.py --check

Output example:

=== fpl-context-mcp configuration check ===

✅ PostgreSQL (RO)   connected (localhost:5432/fpl)
✅ PostgreSQL (ETL)  connected (localhost:5432/fpl)

✅ All required components OK

The command exits with code 0 if all required components pass, or 1 if any required component fails. Note that --check only verifies connectivity — it doesn't tell you whether your tables actually have data in them; for that, see Seeding data.

Dry-run mode

Set DRY_RUN=true to fetch data and verify routing without writing anything to PostgreSQL:

DRY_RUN=true fpl-context-mcp
DRY_RUN=true fpl-context-ingest-match

In dry-run mode:

• Tools return a human-readable description of the call that would have been made — the SQL and database host — without opening any connection.
• Ingestion jobs still call all external APIs (verifying connectivity) but skip every PostgreSQL write. Log output shows how many fixtures and players would have been written.
• The server logs a DRY RUN MODE warning at startup so it is obvious from the logs.

Accepted values for DRY_RUN: true, 1, yes (case-insensitive). Any other value (or absent) disables dry-run.

MCP tools reference

query_historical_stats

Executes a read-only SQL SELECT against the historical stats database.

Parameters

Example prompts

• "Who are the top 10 midfielders by total points this season?"
• "Which players have scored the most goals this season?"
• "Show my captain candidate's goals and points over the last five seasons." (past seasons only cover players still in the current FPL list)
• "When is the next gameweek deadline?"
• "Which teams have the best defensive record at home this season?"
• "Who is injured or doubtful for Arsenal, and what's their chance of playing?"
• "Which players had new injury news in the last 3 days?"

Safety

The tool enforces two layers of protection: a keyword blocklist rejects INSERT, UPDATE, DELETE, DROP, and similar statements before any database call is made, and the database connection uses a read-only role with no write grants.

Live tools overview

These seven tools call the public FPL API directly and need no database or configuration. They share one cache: FPL's bootstrap-static data (every player and team) is downloaded once and reused for 5 minutes across tools, a manager's picks for 2 minutes. If FPL can't be reached, the last cached copy is served and labelled as possibly out of date. All are read-only and advertise readOnlyHint, so clients can skip approval prompts. Team arguments accept a full name, a short name or a unique fragment (Arsenal, MCI, Man City).

get_current_gameweek

No parameters. Returns the current gameweek (in progress or finished), the next gameweek, and the next transfer deadline with the time left. "When is the next deadline?"

get_fixtures

Fixtures with FPL's difficulty rating (FDR): 1 easiest, 5 hardest, from each team's own point of view.

"Arsenal's next six fixtures?", "What are the fixtures in gameweek 12?"

get_fixture_run

For one team you get the average FDR, home/away split, the fixture-by-fixture sequence and any blank or double gameweeks. "Who has the best fixtures for the next six gameweeks?", "Is Chelsea's run good enough to keep Palmer?"

search_players

Each row has price, total points, form, ownership, FPL's expected points for the next gameweek (ep_next) and availability status. "Best midfielders under £8m by form?"

get_xpts

Ranks players by estimated expected points (xPts) next to the opponent and its FDR, expected minutes, and FPL's own ep_next. Double gameweeks count both fixtures; blank ones score zero; flagged players are discounted by FPL's chance of playing.

How xPts is computed. A simple, transparent baseline, not a forecast model: appearance points, plus the player's season xG, xA, clean-sheet, saves and bonus rates per 90 times FPL's scoring values, scaled by expected minutes (the share of available minutes played so far), multiplied by ±10% per FDR point from a neutral 3, and discounted by availability. It extrapolates the season so far, so it is noisy in the first few gameweeks and cannot see rotation, tactics or set-piece changes. Use it to build a shortlist, then cross-check with get_live_availability. "Top five midfielders under £8m by expected points?"

get_manager_squad

Returns the 15-man squad with captain and vice-captain, bench, bank, squad value, transfers and any hit taken, the chip played that week, and every chip used so far this season. It reads only the public data FPL already shows anyone with the team ID; no login. "What chips has team 123456 used?"

get_live_availability

Current FPL injury, suspension and availability flags, fetched live from the FPL API. Use it before recommending or captaining a player, so a newly flagged player isn't missed. It needs no database and no ingestion run.

Parameters (all optional)

With no arguments it returns every player who currently has a flag (any status other than a, or a news note), newest news first, capped at 100 rows. Each row has the player, team, position, status, FPL's chance of playing next round, the news note and when it was added.

Example prompts

• "Is Saka fit for this gameweek?"
• "Who has been suspended or ruled out in the last few days?"
• "Before I set my captain, check that Haaland and Salah have no flags."

How it behaves

• One request to FPL's bootstrap-static endpoint returns every player, and the response is cached in memory for 5 minutes, so heavy use costs FPL only a few calls an hour per server process.
• If FPL can't be reached, the last cached copy is served and labelled as possibly out of date. With no cached copy it returns an error pointing at query_historical_stats, which has availability as of the last ingestion run.

Prompts and resources

Prompts

Ready-made workflows. They contain instructions only, no data, so they never go stale: the tools fetch live FPL data when the prompt runs. Every argument is optional; without team_id the model asks for your squad or answers generally.

Resources

Database schema

The query_historical_stats tool has access to these tables (see db/schema.sql for the full DDL if provisioning standalone):

seasons          id, label (e.g. '2025/26'), start_year, is_current

teams            season_id, fpl_id, name, short_name, strength,
                 strength_attack_home/away, strength_defence_home/away

gameweeks        season_id, gw_number (1–38), deadline_time, is_current,
                 is_next, is_finished, average_entry_score, highest_score

players          season_id, fpl_id, team_fpl_id, first_name, second_name,
                 web_name, position (GKP/DEF/MID/FWD), now_cost, form,
                 total_points, minutes, goals_scored, assists, clean_sheets,
                 expected_goals, expected_assists, ict_index, selected_by_percent,
                 status, chance_of_playing_next_round, news, news_added

fixtures         season_id, fpl_id, gw_number, kickoff_time,
                 home_team_fpl_id, away_team_fpl_id, home_score, away_score,
                 finished, home_team_difficulty, away_team_difficulty

gw_player_stats  season_id, player_fpl_id, gw_number, fixture_fpl_id,
                 opponent_team_fpl_id, was_home, minutes, goals_scored,
                 assists, clean_sheets, bonus, total_points,
                 expected_goals, expected_assists, ict_index, starts

Current vs past seasons: teams, gameweeks, fixtures and gw_player_stats hold the current season only. players also holds one totals-only row per player per past season (see Seeding data for what that covers and what it misses).

Availability: status is a available, d doubtful, i injured, s suspended, u unavailable, n not in squad. chance_of_playing_next_round is 0–100 (NULL means no concern), news is FPL's one-line note, and news_added is when that note last changed. Databases created before 0.7.0 get the news_added column added automatically on the next ingestion run (if the ETL role owns the table; otherwise the job logs the one-line ALTER TABLE to run).

Join hint: teams.fpl_id = players.team_fpl_id (current season, same season_id; team_fpl_id is NULL for past seasons).

Running tests

# Install dev dependencies if you haven't already
pip install -e ".[dev]"

# Run the full suite (all mocked — no real DB or API calls)
pytest tests/ -v

# Lint and format
ruff check . && ruff format .

The test suite covers:

Data sources and disclaimer

fpl-context-mcp is an independent open-source project. It is not affiliated with, endorsed by, or sponsored by the Premier League or Fantasy Premier League.

The package ships no data. The ingestion jobs fetch it, on your machine and under your credentials, from:

You are responsible for complying with each source's terms of use for the data you ingest, store, and — if you host the server for other people — serve. This is especially relevant for commercial use and for public deployments. The MIT license below covers this project's code only, not any third-party content it retrieves.

License

MIT © 2026 Shubham Banthia