# EndzoneAPI (remote · mcp.endzoneapi.com)

Pro football play-by-play, stats, injuries, and odds. REST API and MCP server. Free to start.

- Trust score: 78/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-07

## Components

- remote · `mcp.endzoneapi.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/noahowsh-endzoneapi/mcp.md), [page](https://verifymcp.io/servers/noahowsh-endzoneapi/mcp)

## Channel facts

- Endpoint: `https://mcp.endzoneapi.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-07.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4244 tokens (~235/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the EndzoneAPI MCP server?

EndzoneAPI is a hosted endpoint at https://mcp.endzoneapi.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http noahowsh-endzoneapi 'https://mcp.endzoneapi.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "noahowsh-endzoneapi": {
      "url": "https://mcp.endzoneapi.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "noahowsh-endzoneapi": {
      "type": "http",
      "url": "https://mcp.endzoneapi.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.noahowsh-endzoneapi]
url = "https://mcp.endzoneapi.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "noahowsh-endzoneapi": {
      "type": "remote",
      "url": "https://mcp.endzoneapi.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add noahowsh-endzoneapi --url 'https://mcp.endzoneapi.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  noahowsh-endzoneapi:
    url: "https://mcp.endzoneapi.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "noahowsh-endzoneapi": {
      "Transport": "http",
      "Url": "https://mcp.endzoneapi.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add noahowsh-endzoneapi -t streamable-http -u 'https://mcp.endzoneapi.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "noahowsh-endzoneapi": {
      "type": "http",
      "url": "https://mcp.endzoneapi.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-07 (score 78, +1)

- [security] Tool “get_player_props” rewrote its description, which is the text the model reads

### 2026-10-05 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-03 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-01 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 74, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 73)

First indexed and scored.

## MCP tools (18)

### `list_teams` (~90 tokens)

Use when you need team codes, or all 32 current teams with conference, division, colours, and logo URLs. Team codes are nflverse spelling (LA for the Rams, WAS for Washington). Cheapest tool at 1 credit.

Input parameters:

- `conference` (string): Filter by conference
- `division` (string): Filter by division, e.g. 'AFC East' or 'NFC West'

Output parameters:

- `count` (number)
- `teams` (array)

### `get_standings` (~137 tokens)

Use for regular-season standings and playoff seeding: record, win%, points for/against, home/away/division/conference records, streak, division rank, and conference seed. Ranks apply the real NFL tiebreaking procedure and report which step decided each one. Computed from final scores. Defaults to the current season. Costs 2 credits.

Input parameters:

- `conference` (string): Filter by conference
- `division` (string): Filter by division, e.g. 'NFC North'
- `season` (string|number): Season year the regular season starts (e.g. 2025). Defaults to current.

Output parameters:

- `count` (number)
- `note` (string)
- `season` (number)
- `standings` (array)

### `get_team_stats` (~110 tokens)

Use for one team's season: totals (passing, rushing, receiving, defense, kicking, penalties), EPA per play, yards per attempt/carry, the standings row, and every weekly stat line. Costs 5 credits.

Input parameters:

- `season` (string|number): Season year (e.g. 2025). Defaults to current.
- `season_type` (string): Regular season (default) or postseason
- `team` (string, required): Team code (e.g. KC, BUF, PHI)

Output parameters:

- `count` (number)
- `record`
- `season` (number)
- `season_type` (string)
- `team`
- `totals` (object)
- `weeks` (array)

### `get_games` (~203 tokens)

Use when querying past or future games with filters: season, week, team, date range, game type, status. Returns scores, kickoff (UTC), venue, rest days, starting QBs, coaches, referee, and the consensus closing spread, total, and moneylines. For upcoming-only games prefer get_schedule (2 cr). Costs 5 credits.

Input parameters:

- `date_from` (string): Start date YYYY-MM-DD
- `date_to` (string): End date YYYY-MM-DD
- `game_type` (string): REG, WC, DIV, CON, SB, or POST for any playoff game
- `limit` (integer): Max results (default 100)
- `season` (string|number): Season year (e.g. 2025)
- `status` (string): Game status
- `team` (string): Team code (home or away)
- `week` (integer): Week number (1-18 regular season; 19+ postseason)

Output parameters:

- `count` (number)
- `filters` (object)
- `games` (array)

### `get_schedule` (~104 tokens)

Use to see what is coming up: unplayed games in the next N days (default 7), or a specific week of the current season. Includes consensus lines where posted. Costs 2 credits.

Input parameters:

- `days` (integer): Days ahead to look when week is not set (default 7)
- `team` (string): Team code to filter
- `week` (integer): A specific week of the current season (returns all games that week, played or not)

Output parameters:

- `count` (number)
- `days` (number|null)
- `season` (number)
- `upcoming_games` (array)
- `week` (number|null)

### `get_game_detail` (~91 tokens)

Use when you need everything about one game: both teams, full team box-score stats (EPA, success, drives), consensus closing line, per-bookmaker opening/closing/latest odds, weather, surface, and officials. Requires a game id from get_games or get_schedule. Costs 10 credits.

Input parameters:

- `game_id` (string, required): Game id, e.g. 2025_01_KC_BUF

Output parameters:

- `away_team`
- `consensus_closing` (object)
- `game` (object)
- `home_team`
- `odds` (object)
- `officials` (array)
- `team_stats` (object)

### `get_head_to_head` (~100 tokens)

Use to compare two teams' history: recent meetings with scores, the win/loss record between them, and average margin. Filter by season or get all-time. Costs 10 credits.

Input parameters:

- `limit` (integer): Max games (default 20)
- `season` (string|number): Season year. Omit for all-time.
- `team1` (string, required): First team code
- `team2` (string, required): Second team code

Output parameters:

- `avg_margin_team1` (number|null)
- `count` (number)
- `games` (array)
- `record` (object)
- `team1` (string)
- `team2` (string)
- `total_games` (number)

### `search_players` (~170 tokens)

Use to find a player by name (partial match). Searches ~25,000 players back to 1999; returns current-season players by default, falling back to all players back to 1999 when none match. Returns the GSIS player id needed by get_player_stats. Costs 2 credits.

Input parameters:

- `active` (boolean): Default true, but an active-only search that finds nobody automatically falls back to all players and says so. Set false to search everyone outright.
- `limit` (integer): Max results (default 10)
- `position` (string): Filter by position (e.g. QB, RB, WR, TE, OL, DL, LB, DB)
- `query` (string, required): Player name or part of it
- `team` (string): Filter by current team code

Output parameters:

- `count` (number)
- `included_inactive` (boolean)
- `note` (string)
- `players` (array)

### `get_player_stats` (~137 tokens)

Use for one player: bio, draft, physicals, headshot, id crosswalk (PFR, ESPN), summed season totals across passing, rushing, receiving, defense, kicking, returns, and fantasy points, every weekly stat line for the season, and games played per season. Defaults to the player's latest season. Costs 5 credits.

Input parameters:

- `player_id` (string, required): GSIS player id from search_players (e.g. 00-0033873)
- `season` (string|number): Season year. Defaults to the player's latest season.
- `season_type` (string): Regular season (default) or postseason

Output parameters:

- `count` (number)
- `player` (object)
- `season` (number)
- `season_totals` (object)
- `season_type` (string)
- `seasons` (array)
- `weeks` (array)

### `get_player_leaders` (~214 tokens)

Use to rank players on any weekly stat over a season: passing_yards, passing_tds, rushing_yards, receiving_yards, receptions, targets, def_sacks, def_interceptions, fantasy_points_ppr, passing_epa, rushing_epa, receiving_epa, and ~130 more. Counting stats are summed, rate stats averaged. Filter by position, team, minimum games. Costs 5 credits.

Input parameters:

- `limit` (integer): Max results (default 20)
- `min_games` (integer): Minimum games with a stat line (default 1)
- `position` (string): Position filter, e.g. QB, RB, WR, TE
- `season` (string|number): Season year. Defaults to current.
- `season_type` (string): Regular season (default) or postseason
- `stat` (string, required): Weekly stat column to rank by (e.g. passing_yards, receiving_epa, def_sacks)
- `team` (string): Team code filter

Output parameters:

- `aggregation` (string)
- `count` (number)
- `leaders` (array)
- `season` (number)
- `season_type` (string)
- `stat` (string)

### `get_injuries` (~119 tokens)

Use for the official injury report: game status (Out, Doubtful, Questionable) and practice participation with the injury named, by team and week. Defaults to the latest reported week of the current season. Costs 2 credits.

Input parameters:

- `season` (string|number): Season year. Defaults to current.
- `status` (string): Filter by game status: Out, Doubtful, Questionable
- `team` (string): Team code
- `week` (integer): Week. Defaults to the latest week with a report.

Output parameters:

- `count` (number)
- `injuries` (array)
- `season` (number)
- `week` (number)

### `get_depth_chart` (~97 tokens)

Use for a team's depth chart by week: formation, position, depth rank, player. Defaults to the latest week available. Costs 2 credits.

Input parameters:

- `formation` (string): Filter by formation/unit, e.g. Offense, Defense, Special Teams
- `season` (string|number): Season year. Defaults to current.
- `team` (string, required): Team code
- `week` (integer): Week. Defaults to latest.

Output parameters:

- `count` (number)
- `depth_chart` (array)
- `season` (number)
- `team` (string)
- `week` (number)

### `get_snap_counts` (~136 tokens)

Use for playing time: offensive, defensive, and special-teams snaps and snap shares, for one game, one player (PFR id), or a team's season. Costs 5 credits.

Input parameters:

- `game_id` (string): Game id, e.g. 2025_01_KC_BUF
- `limit` (integer): Max rows (default 200)
- `player_id` (string): PFR player id (from search_players pfr_id)
- `season` (string|number): Season year (with team or player)
- `team` (string): Team code
- `week` (integer): Week filter

Output parameters:

- `count` (number)
- `filters` (object)
- `note` (string)
- `snap_counts` (array)

### `get_plays` (~619 tokens)

Use for play-by-play with nflfastR metrics: EPA, WPA, win probability, success, CPOE, air yards, formation flags, and the players involved. Filter by game, or by season plus week/team/player, plus play type, down, quarter, win-probability band, red zone, third down. Set include_charting for FTN manual charting from 2022 on -- alignment, pre-snap motion, play action, screens, run-pass options, blitzer counts, drops -- or filter directly on those flags. Returns a per-query EPA and success-rate summary. Paginate with offset. Costs 10 credits.

Input parameters:

- `defteam` (string): Defense team code
- `down` (integer): Down
- `game_id` (string): Game id, e.g. 2025_01_KC_BUF
- `include_charting` (boolean): Attach FTN manual charting to each play (2022+): alignment, motion, play action, screens, RPO, blitzers, drops
- `is_drop` (boolean): Charting filter: charted drop (2022+)
- `is_motion` (boolean): Charting filter: pre-snap motion (2022+)
- `is_no_huddle` (boolean): Charting filter: no huddle (2022+)
- `is_play_action` (boolean): Charting filter: play action (2022+)
- `is_qb_out_of_pocket` (boolean): Charting filter: quarterback out of the pocket (2022+)
- `is_rpo` (boolean): Charting filter: run-pass option (2022+)
- `is_screen_pass` (boolean): Charting filter: screen pass (2022+)
- `is_trick_play` (boolean): Charting filter: trick play (2022+)
- `limit` (integer): Max plays (default 200)
- `max_wp` (number): Maximum pre-play win probability
- `min_blitzers` (integer): Charting filter: at least this many blitzers (2022+). FTN counts rushers beyond the base rush, so this is typically 0-3; 5+ is almost never charted.
- `min_wp` (number): Minimum pre-play win probability for the offense
- `offset` (integer): Pagination offset
- `passer_id` (string): GSIS id of the passer
- `play_type` (string): Play type
- `posteam` (string): Offense team code
- `quarter` (integer): Quarter (5+ = overtime)
- `receiver_id` (string): GSIS id of the receiver
- `red_zone` (boolean): Only plays inside the 20
- `rusher_id` (string): GSIS id of the rusher
- `season` (string|number): Season year (required when game_id is not set)
- `third_down` (boolean): Only third downs
- `week` (integer): Week

Output parameters:

- `charted_plays` (number)
- `count` (number)
- `next_offset` (number|null)
- `note` (string)
- `plays` (array)
- `summary` (object)

### `get_advanced_stats` (~251 tokens)

Use for tracking and charting metrics the box score does not carry. Next Gen Stats (2016+): time to throw, air yards, completion percentage above expectation, separation, cushion, rush yards over expected. Pro Football Reference advanced (2018+): pressures, hurries, blitzes, drops, bad throws, missed tackles, coverage yards allowed. Pick a source, then filter by season, week, player or team. Costs 5 credits.

Input parameters:

- `limit` (integer): Max rows (default 50)
- `player_id` (string): GSIS id for an ngs_* source, PFR id for a pfr_* source; both are on search_players
- `season` (string|number): Season year. Defaults to current. NGS from 2016, PFR from 2018.
- `source` (string, required): Which dataset: ngs_passing, ngs_rushing, ngs_receiving, pfr_passing, pfr_rushing, pfr_receiving, pfr_defense
- `team` (string): Team code
- `week` (integer): Week. NGS also publishes week 0 as the season aggregate.

Output parameters:

- `count` (number)
- `metric_keys` (array)
- `note` (string)
- `player_id_kind` (string)
- `season` (number)
- `source` (string)
- `stats` (array)

### `get_odds` (~370 tokens)

Use for betting lines. Pass game_id for one game (10 credits): the consensus closing spread/total/moneyline (every game since 1999) plus per-bookmaker opening, closing and latest lines from the 2020 season (up to 8 books, including Pinnacle). Or pass season (optionally team) for a season of per-book closing lines in one call, with final scores and the consensus close, at 10 credits per game returned, 100 games a page by default (up to 500); each book's line is an array in the order given by columns. For consensus closing lines only, get_games returns a whole season for 5 credits. Set estimate_only to get the price without being charged.

Input parameters:

- `bookmaker` (string): Bookmaker key (draftkings, fanduel, betmgm, espnbet, pinnacle, bovada, betonlineag, mybookieag)
- `estimate_only` (boolean): Return what this call would cost, without charging or running it.
- `game_id` (string): Game id, e.g. 2026_01_KC_BUF. Omit and pass season for a whole season.
- `limit` (integer): With season: games per page (default 100, max 500).
- `offset` (integer): With season: page offset; use next_offset from the previous page.
- `season` (string|number): Season year for a whole season of per-book lines, e.g. 2026. Used when game_id is not set.
- `snapshot_type` (string): Single game: one snapshot type (default all). Season: opening or closing (default closing).
- `team` (string): With season: only this team's games (e.g. KC).

Output parameters:

- `away_team` (string)
- `bookmaker_count` (number)
- `books` (array)
- `columns` (array)
- `consensus_closing` (object)
- `count` (number)
- `credits` (number)
- `credits_per_game` (number)
- `estimate_only` (boolean)
- `game_id` (string)
- `games` (array)
- `home_team` (string)
- `kickoff` (string|null)
- `next_offset` (number|null)
- `note` (string)
- `season` (string)
- `snapshot_type` (string)
- `tool` (string)
- `total_games` (number)

### `get_line_movement` (~78 tokens)

Use to see how a game's lines moved: the full time series of hourly snapshots grouped by bookmaker. Most expensive tool (25 cr); use get_odds (10 cr) if you only need opening, closing, or current lines.

Input parameters:

- `bookmaker` (string): Bookmaker key filter
- `game_id` (string, required): Game id

Output parameters:

- `away_team` (string)
- `game_id` (string)
- `home_team` (string)
- `kickoff` (string|null)
- `movement` (object)
- `snapshots` (number)

### `get_player_props` (~336 tokens)

Use for player prop lines by sportsbook: over/under on passing yards, passing TDs, rushing yards, receiving yards and receptions, plus anytime TD, from the 2023 season (7 books: DraftKings, FanDuel, BetMGM, ESPN BET, Pinnacle, Bovada, BetOnline). Pass game_id for every player's props in one game (10 credits), or player_id with season for one player across a season (10 credits per game returned). Returns the closing line by default (the last before kickoff) or the opening line. Set estimate_only to get the price without being charged.

Input parameters:

- `bookmaker` (string): Bookmaker key, e.g. draftkings, fanduel, pinnacle.
- `estimate_only` (boolean): Return what this call would cost, without charging or running it.
- `game_id` (string): Game id, e.g. 2025_01_KC_LAC.
- `market` (string): One market: player_pass_yds (passing yards), player_pass_tds (passing touchdowns), player_rush_yds (rushing yards), player_reception_yds (receiving yards), player_receptions (receptions), player_anyt…
- `player_id` (string): GSIS player id (00-00XXXXX) from search_players. With season: that player's props across the season.
- `season` (string|number): Season year, with player_id.
- `snapshot_type` (string): closing (default): the last line before kickoff. opening: the first one captured.

Output parameters:

- `count` (number)
- `credits` (number)
- `credits_per_game` (number)
- `estimate_only` (boolean)
- `games` (number)
- `note` (string)
- `props` (array)
- `snapshot_type` (string)
- `tool` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/noahowsh-endzoneapi/mcp#diagnostics

## Score history

- 2026-10-07: 78
- 2026-10-05: 77
- 2026-10-04: 76
- 2026-10-03: 76
- 2026-10-02: 75
- 2026-10-01: 75
- 2026-09-30: 74
- 2026-09-29: 74
- 2026-09-28: 74
- 2026-09-27: 73

## Common questions

### What is the EndzoneAPI MCP server?

EndzoneAPI is an MCP server listed in the public MCP registry as io.github.noahowsh/endzoneapi. Pro football play-by-play, stats, injuries, and odds. REST API and MCP server. Free to start. This page covers its hosted endpoint (https://mcp.endzoneapi.com/mcp).

### Is the EndzoneAPI MCP server safe to use?

EndzoneAPI scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the EndzoneAPI MCP server expose?

EndzoneAPI exposes 18 tools: list_teams, get_standings, get_team_stats, get_games, get_schedule, and 13 more. Their descriptions and schemas cost roughly 3,362 tokens of context every time the server is loaded.

### Does the EndzoneAPI MCP server require authentication?

Yes. EndzoneAPI asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the EndzoneAPI MCP server still maintained?

EndzoneAPI is still listed as active in the MCP registry. We last reached this channel on 7 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.endzoneapi.com/mcp
- Authorisation metadata: https://mcp.endzoneapi.com/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/noahowsh/endzoneapi-mcp
- Changelog RSS feed: https://verifymcp.io/servers/noahowsh-endzoneapi/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/noahowsh-endzoneapi/mcp.json
- HTML version of this page: https://verifymcp.io/servers/noahowsh-endzoneapi/mcp