EndzoneAPI MCP server

The football data API. Play-by-play with EPA and win probability, player and team stats, schedules, injuries, depth charts and closing lines for every NFL game since 1999. REST API and MCP server. 500 free credits every month, no card.

Website: https://endzoneapi.com · Docs: https://endzoneapi.com/docs · Get a key: https://endzoneapi.com/signup

You:    "What was the closing spread for every Chiefs game last season?"
Claude: [calls get_games -> one call, every game with spread, total and moneyline]

You:    "Which offenses had the best EPA per play on third down in 2025?"
Claude: [calls get_plays with third_down filter -> EPA already attached]

Skills

16 free Claude skills turn Claude into a football analyst wired to these tools: EPA per play and success rate, Next Gen Stats, weekly player stats, odds and devigging, prop modeling, college football and FCS, and honest backtesting. They are plain markdown folders.

git clone https://github.com/noahowsh/endzoneapi-mcp.git

Or install them as a Claude Code plugin:

/plugin marketplace add noahowsh/endzoneapi-mcp
/plugin install endzoneapi-skills@endzoneapi

Or with the skills CLI: npx skills add noahowsh/endzoneapi-mcp.

Point Claude (Claude Code, or any client that loads skills) at the skills/ folder, and connect the MCP server above so the skills can call live data. The dispatch skill routes a request to the right two or three skills. Full list: skills/README.md

You:    "Which offenses were best on third down in 2025, and how many plays is that based on?"
Claude: [loads epa-analysis + endzoneapi-tool, calls get_plays with third_down and a limit that
         holds the split, reports EPA per play, success rate and the play count]

Related MCP server: nfl-mcp

Useful pages

• Odds this week: https://endzoneapi.com/odds

• Player props this week (best price per player across books): https://endzoneapi.com/props

• Props guides: receiving yards history, anytime touchdown history, passing yards history

• Guides: https://endzoneapi.com/guides

• Docs: https://endzoneapi.com/docs

• Pricing: https://endzoneapi.com/pricing

• Data coverage: https://endzoneapi.com/data

• College football (FBS): https://endzoneapi.com/college-football

• FCS football: https://endzoneapi.com/fcs-football

• Compare: ESPN API alternative, nflfastR API, SportsDataIO alternative

Python

The official Python client is on PyPI: endzoneapi.

pip install endzoneapi
export ENDZONEAPI_API_KEY=sk_live_...

from endzoneapi import Client, to_dataframe

client = Client()

print(client.get_player_props(game_id="2025_01_KC_LAC", estimate_only=True))

props = client.get_player_props(
    game_id="2025_01_KC_LAC",
    market="player_pass_yds",
    bookmaker="draftkings",
)
df = to_dataframe(props, key="props")
print(df[["player_name", "line", "over_odds", "under_odds"]])

Typed errors for a bad key, no credits left, not found and rate limits, automatic retries, and to_dataframe for pandas.

Quick start

This is a hosted (remote) MCP server over Streamable HTTP. There is nothing to install.

Claude Code

claude mcp add --transport http endzoneapi "https://mcp.endzoneapi.com/mcp?key=YOUR_API_KEY"

Claude Desktop, Cursor and other clients

{
  "mcpServers": {
    "endzoneapi": {
      "url": "https://mcp.endzoneapi.com/mcp?key=YOUR_API_KEY"
    }
  }
}

The key can also be sent as an x-api-key header or Authorization: Bearer. Connecting and listing tools works without a key; calling a tool needs one.

REST

curl -X POST https://mcp.endzoneapi.com/v1/list_teams -H "x-api-key: YOUR_API_KEY"

Every tool is POST /v1/{tool} with a JSON body.

Tools (18)

Data

• Play-by-play for every game since 1999 with EPA, win probability and model columns

• Closing spread, total and moneyline for every game since 1999; per-book odds from 2020 (up to 8 books, hourly in season from 2026)

• Player prop lines from 2023, captured live before every game

• Weekly player and team stats, injuries (2009+), depth charts (2001+), snap counts (2012+), Next Gen Stats, FTN charting (2022+)

Coverage by season, read live from the database: https://endzoneapi.com/data/historical-odds, https://endzoneapi.com/data/player-props and https://endzoneapi.com/data/play-by-play

Used by

NoPunt, our NFL predictions site, runs on this API.

• nfl-props-backtest: a season of NFL player props against what happened (calibration, over rates, line moves, anytime TD prices), in Python and R.

Pricing

500 free credits every month, no card. Plans: Starter $19/mo (10,000 credits), Pro $49/mo (30,000), Scale $149/mo (125,000). Wallet top-ups from $5, kept while your account is open. https://endzoneapi.com/pricing

Attribution

Stats, schedules and play-by-play are from nflverse (CC BY 4.0), modified and combined with our own models. Not affiliated with the NFL or any team.

License

MIT for the contents of this repository. Data terms as above.

Use with Codex

Add this repo as a Codex plugin marketplace, then install the plugin:

codex plugin marketplace add noahowsh/endzoneapi-mcp

Then open the plugin directory in Codex and install endzoneapi-skills from the endzoneapi marketplace. The plugin bundles the skills in skills/ and the EndzoneAPI MCP server (https://mcp.endzoneapi.com/mcp). Set your key first (free at https://endzoneapi.com/signup):

export ENDZONEAPI_API_KEY=your_key

Codex sends it as a bearer token.

Use with Gemini CLI

export ENDZONEAPI_API_KEY=your_key
gemini extensions install https://github.com/noahowsh/endzoneapi-mcp

The extension adds the EndzoneAPI MCP server (https://mcp.endzoneapi.com/mcp) and sends the key in the x-api-key header. Get a free key (500 credits a month) at https://endzoneapi.com/signup.