Skip to main content
Glama
io.github.christianclaudio/espn

io.github.christianclaudio/espn

🏈 mcp-server-espn

CI PyPI Python License: Apache-2.0 Coverage CodeRabbit Reviews

Enterprise-grade Model Context Protocol (MCP) server for live and historical sports analytics, consensus betting odds, and predictions via ESPN.
Equips AI agents with real-time sports intelligence, live win probabilities, in-depth boxscore statistics, roster hierarchies, and matchup analytics.


⚠️ Disclaimers & Fair Use Notice

IMPORTANT

Community Project Disclaimer
mcp-server-espn is an independent open-source community project. It is not affiliated with, sponsored by, endorsed by, or supported by ESPN Inc. or The Walt Disney Company. "ESPN" is a trademark of ESPN Inc. All data provided via ESPN's public REST endpoints is intended for educational, research, and personal non-commercial use.


Related MCP server: Sports Betting MCP

💡 Why This Exists

Autonomous sports analysis requires high-velocity, structured, and resilient data feeds:

  1. Live Game State & Win Probability: Real-time game events (turnovers, scoring plays, pitching changes) shift momentum and expected outcomes dynamically.

  2. Key Player Injuries & Depth Chart Swaps: An in-game injury or substitution fundamentally alters team efficiency and tactical matchups.

  3. Consensus Odds & Predictive Models: Aggregating consensus sportsbook lines (DraftKings, Caesars, ESPN BET) alongside predictive metrics (FPI, BPI) powers deep statistical game evaluations.

mcp-server-espn provides a unified, hardened Model Context Protocol interface directly to ESPN's public sports data endpoints.


🏟️ System Architecture

graph TD
    Client["AI Agent / MCP Client<br>(Antigravity, Claude, Codex, Cortex)"]
    Gateway["Root FastMCP Gateway (espn-mcp)<br>(stdio / Streamable HTTP)"]
    ParentMW["Parent Middleware Pipeline<br>(ParentAuditMiddleware & ReadOnlyGateMiddleware)"]
    GamesSub["Sub-Server: espn-games<br>(games_* | GamesDomainGuard)"]
    TeamsSub["Sub-Server: espn-teams<br>(teams_* | TeamsDomainGuard)"]
    NewsSub["Sub-Server: espn-news<br>(news_* | Resources)"]
    ClientHandler["Hardened ESPN AsyncClient<br>(Connection Pool & 429 Jitter Backoff)"]
    ESPN["ESPN Public REST CDN<br>(https://site.web.api.espn.com)"]

    Client <-->|"JSON-RPC (tools/list, tools/call)"| Gateway
    Gateway --> ParentMW
    ParentMW --> GamesSub
    ParentMW --> TeamsSub
    ParentMW --> NewsSub
    GamesSub & TeamsSub & NewsSub <-->|"API Methods"| ClientHandler
    ClientHandler <-->|"HTTPS REST Mirror"| ESPN

🚀 FastMCP 4 Server Composition

mcp-server-espn implements canonical FastMCP 4 Server Composition via root.mount(..., namespace="..."):

  • Domain Sub-Servers: Partitioned into espn-games (games_*), espn-teams (teams_*), and espn-news (news_*).

  • Hierarchical Middleware:

    • Parent: ParentAuditMiddleware (timing logs, audit trails, and secret scrubbing) and ReadOnlyGateMiddleware (fail-closed read-only enforcement).

    • Child: GamesDomainGuardMiddleware (query limit validation <= 100) and TeamsDomainGuardMiddleware (team and athlete identifier validation).

  • Focused Profiles: Run lightweight surfaces via --profile full|games|teams|news|readonly (ESPN_MCP_PROFILE):

    • full (default): All 33 domain tools and resources mounted.

    • games: Scores, summaries, schedules, standings, rankings, transactions, league leaders, draft, live play-by-play, situations, odds, probabilities, predictor, calendar, futures, power index (20 tools).

    • teams: Rosters, depth charts, player stats, athlete profiles, bio, stats, gamelog, splits, search, list teams, team detail, team statistics (12 tools).

    • news: League news and reference resources (1 tool).

    • readonly: Read-only enforcement across all routes.

  • Opt-In Tool Search: Preserves standard flat tools/list by default for seamless client compatibility, while enabling search transforms via --enable-tool-search (ESPN_MCP_ENABLE_TOOL_SEARCH): BM25 ranking for natural-language queries by default (search_tools takes a query), or regex patterns with --tool-search-backend regex (ESPN_MCP_TOOL_SEARCH_BACKEND=regex; search_tools takes a pattern).


📈 Sports Intelligence Workflows

Workflow 1: Live In-Game Win Probability & Situation Tracking

  1. Poll Active Games: Agent calls games_get_scoreboard(sport="football", league="nfl") to identify close games in the 2nd half.

  2. Fetch In-Game Situation & Win Probability: Call games_get_game_situation(sport="football", league="nfl", event_id="401872947") and games_get_win_probabilities(sport="football", league="nfl", event_id="401872947") to inspect down/distance, red zone state, and live win expectancy curve.

  3. Inspect Play-by-Play: Call games_get_play_by_play(sport="football", league="nfl", event_id="401872947") for drive-by-drive sequencing and scoring event logs.

Workflow 2: Athlete Deep Dive & Fantasy Valuation

  1. Bio & Career Context: Call teams_get_athlete_bio(sport="football", league="nfl", athlete_id="12483") to retrieve draft capital, college pedigree, and physical metrics.

  2. Recent Gamelog & Splits: Pull teams_get_athlete_gamelog and teams_get_athlete_splits to analyze performance trends against specific defensive schemes and venue conditions.

  3. League-Wide Leaderboard Standing: Call games_get_leaders_by_athlete(sport="football", league="nfl", category="passing", sort="yards") to evaluate percentile rankings.


🏟️ Supported Sports & Leagues Reference Matrix

The server supports canonical sport/league slug pairs and auto-normalizes popular shortcuts:

Sport Slug

League Slug

Recognized Shortcuts / Aliases

Common Display Name

football

nfl

nfl

National Football League

football

college-football

cfb, ncaa-football, fbs

NCAA College Football

basketball

nba

nba

National Basketball Association

basketball

mens-college-basketball

cbb, ncaa-basketball

NCAA Men's College Basketball

basketball

womens-college-basketball

wbb, ncaa-womens-basketball

NCAA Women's Basketball

basketball

wnba

wnba

Women's National Basketball Association

baseball

mlb

mlb

Major League Baseball

hockey

nhl

nhl

National Hockey League

soccer

eng.1

epl, premier-league

English Premier League

soccer

usa.1

mls

Major League Soccer

soccer

uefa.champions

ucl, champions-league

UEFA Champions League

soccer

esp.1

la-liga

Spanish La Liga

soccer

ita.1

serie-a

Italian Serie A

soccer

ger.1

bundesliga

German Bundesliga

soccer

fra.1

ligue-1

French Ligue 1


📊 Tool Suite (33 Domain Tools)

All tools implement explicit MCP 2.0 annotations (readOnlyHint=True, idempotentHint=True):

Domain

Tool

Parameters

Description

Games

games_get_scoreboard

sport, league, date, week, season_type, group, limit

Final scores and results for any date (date=YYYYMMDD) or inclusive date range (date=YYYYMMDD-YYYYMMDD; ranges of up to 31 days are fetched one day at a time, because ESPN rejects the range form on team-sport scoreboards, so limit applies to each day (up to 31 × limit events) and one failed day fails the whole call; golf ranges are sent to ESPN as is), plus live scores, state (pre/in/post), period/clock, TV broadcasts, starting probables. Returns event IDs for other game tools.

Games

games_get_game_summary

sport, league, event_id

Consensus betting lines, matchup predictor win %, ATS, scoring plays, drives, leaders, momentum.

Games

games_get_team_schedule

sport, league, team_id, season, season_type

Season schedule with historical game results and scores: the regular season by default, postseason games with season_type=3.

Games

games_get_standings

sport, league, season

Division, conference, and overall league standings, win-loss records, games back, and win percentages. season is the year the season ends (2016 = the 2015-16 NBA season), or the year it starts for soccer (2026 = the 2026-27 Premier League season); the response echoes requested_season, season, and season_display.

Games

games_get_rankings

sport, league

Top 25 national polls and rankings (AP Top 25, Coaches Poll, College Football Playoff).

Games

games_get_transactions

sport, league, limit

League-wide transactions, roster trades, waivers, signings, and releases.

Games

games_get_leaders_by_athlete

sport, league, limit, category, sort

Statistical leaderboards across players in a league.

Games

games_get_leaders_by_team

sport, league, limit, category, sort

Team statistical rankings and leaderboards.

Games

games_get_league_groups

sport, league

League conference, division, and structural group hierarchies.

Games

games_get_league_events

sport, league, dates

The league's current scheduled events. ESPN's events route ignores dates, so date filtering is not supported: a dates value returns isError: true with no request, pointing to games_get_scoreboard with the same value as date.

Games

games_get_league_draft

sport, league, season

League draft rounds, team selections, and pick results.

Games

games_get_scoreboard_header

sport, league

Live ticker scoreboard header data across games for a sport and league.

Games

games_get_event_odds

sport, league, event_id, competition_id

Sportsbook consensus and provider odds (spreads, totals, moneylines).

Games

games_get_play_by_play

sport, league, event_id, limit, page

Play-by-play sequence, clock, scoring, and drive events.

Games

games_get_game_situation

sport, league, event_id

Real-time in-game situation (down, distance, yardline, possession, red zone).

Games

games_get_win_probabilities

sport, league, event_id

Live and historical win probability curves across game progression.

Games

games_get_game_predictor

sport, league, event_id

Pre-game and in-game matchup predictor and projection metrics.

Games

games_get_calendar

sport, league, dates

League schedule calendar and active event dates across a season.

Games

games_get_futures

sport, league, season

Season futures betting markets (championship odds, win totals).

Games

games_get_power_index

sport, league, season

Team power index (FPI / BPI) ratings and efficiency metrics.

Teams

teams_search

query, type, limit

Global search for athletes and teams by name/keyword (type="player" or "team").

Teams

teams_list_teams

sport, league

Directory of all franchises/teams in a specified league with IDs, names, and logos.

Teams

teams_get_team

sport, league, team_id

Team detail overview, venue, record, standings summary, and upcoming scheduled event.

Teams

teams_get_team_statistics

sport, league, team_id

Comprehensive team and opponent statistical category splits (passing, rushing, etc.).

Teams

teams_get_team_roster

sport, league, team_id

Full active roster grouped by position, coach info, jersey numbers, and injury status.

Teams

teams_get_team_depth_chart

sport, league, team_id

Positional starter/backup hierarchy (QB1, QB2, etc.) to model injury substitution impacts.

Teams

teams_get_player_stats

sport, league, event_id

Boxscore statistics for individual athletes across game categories.

Teams

teams_get_athlete_overview

sport, league, athlete_id

Athlete biographical info, season/career stats, game logs, next game, and rotowire notes.

Teams

teams_get_athlete_bio

sport, league, athlete_id

Detailed athlete background, draft history, birth details, college pedigree.

Teams

teams_get_athlete_stats

sport, league, athlete_id, season

Full seasonal and career category statistics for an athlete.

Teams

teams_get_athlete_gamelog

sport, league, athlete_id, season

Game-by-game performance log for an athlete across a season.

Teams

teams_get_athlete_splits

sport, league, athlete_id, season

Situational statistical splits (home/away, turf/grass, monthly, vs opponents).

News

news_get_news

sport, league, limit

Recent news headlines, injury designations, and breaking roster analysis.


🏃 Quickstart & Installation

1. Run Directly via uvx (Zero Install)

Console scripts in [project.scripts] both call espn_mcp.server:main: espn-mcp (used below) and mcp-server-espn. Install examples stay unpinned. To freeze a release, pin the version from Releases.

uvx --from mcp-server-espn espn-mcp

After an upgrade, reload the MCP host so the live process start time is after the new binary mtime (stale process ≠ new package).

2. Install via pip or uv

# Using pip
pip install mcp-server-espn

# Using uv
uv add mcp-server-espn

3. Run via Docker

docker run --rm -i ghcr.io/christianclaudio/mcp-server-espn:latest

🎛️ Engine Configuration

Variable

CLI Flag

Default

Description

ESPN_BASE_URL

—

https://site.web.api.espn.com

Target ESPN REST CDN base URL (bypasses Akamai TLS filter)

ESPN_TIMEOUT_SECONDS

—

30.0

HTTP request timeout in seconds

ESPN_MCP_AUTH_TOKEN

—

unset

Shared bearer token required on HTTP transports (stdio ignores it)

ESPN_MCP_ALLOW_UNAUTHENTICATED_BIND

—

unset

1 accepts a tokenless HTTP bind to a non-localhost host

ESPN_MAX_RETRIES

—

3

Maximum retry attempts on 429 / 5xx with jittered exponential backoff, waiting longer when Retry-After asks (capped at ESPN_TIMEOUT_SECONDS)

ESPN_MCP_READONLY

—

0

Restrict server strictly to read-only inspection tools

ESPN_MCP_PROFILE

--profile

full

Domain sub-server profile: full, games, teams, news, readonly

ESPN_MCP_ENABLE_TOOL_SEARCH

--enable-tool-search

0

Replace flat tool catalog with dynamic search transform (search_tools + call_tool)

ESPN_MCP_TOOL_SEARCH_BACKEND

--tool-search-backend

bm25

Tool Search backend: bm25 (BM25SearchTransform, natural-language ranking; search_tools takes query) or regex (RegexSearchTransform, regex patterns; search_tools takes pattern)


🎮 Client Integration Guides

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

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": ["--from", "mcp-server-espn", "espn-mcp"],
      "env": {
        "ESPN_TIMEOUT_SECONDS": "20.0"
      }
    }
  }
}

For Claude Code CLI:

claude mcp add espn -- uvx --from mcp-server-espn espn-mcp

Add to .agents/mcp_config.json or ~/.gemini/config/mcp_config.json:

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": ["--from", "mcp-server-espn", "espn-mcp"],
      "env": {
        "ESPN_TIMEOUT_SECONDS": "20.0"
      },
      "lazy": true
    }
  }
}

Add to ~/.snowflake/cortex/mcp.json:

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": ["--from", "mcp-server-espn", "espn-mcp"],
      "env": {
        "ESPN_TIMEOUT_SECONDS": "20.0"
      },
      "lazy": true
    }
  }
}

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": ["--from", "mcp-server-espn", "espn-mcp"]
    }
  }
}

Add to cline_mcp_settings.json or .vscode/settings.json:

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": ["--from", "mcp-server-espn", "espn-mcp"]
    }
  }
}

Launch the FastMCP server over modern Streamable HTTP:

uvx --from mcp-server-espn espn-mcp --transport streamable-http --host 127.0.0.1 --port 8000

Connect Streamable HTTP clients to http://127.0.0.1:8000/mcp (FastMCP's default Streamable HTTP path).

In the default (stateful) HTTP mode, a session idle for 30 minutes expires: its next request gets HTTP 404 and the client must start a new session. Change this with FastMCP's session_idle_timeout (on http_app()) or FASTMCP_HTTP_SESSION_IDLE_TIMEOUT (seconds, or none to never expire); see the FastMCP 4.1.0 release and #5229.

HTTP authentication. Set ESPN_MCP_AUTH_TOKEN to require Authorization: Bearer <token> on every HTTP request; a missing or wrong token gets 401. The token is stripped, and a blank value counts as unset. It is attached when the server is built, so espn-mcp, fastmcp run and an ASGI host mounting mcp.http_app() all enforce it. stdio never uses it.

With no token, espn-mcp refuses an HTTP bind to any host other than 127.0.0.1, ::1 or localhost and exits with code 2. Set the token, bind to localhost, or set ESPN_MCP_ALLOW_UNAUTHENTICATED_BIND=1 to accept an unauthenticated public bind. Other entry points get the token but not the localhost check: fastmcp run and http_app() do not go through espn-mcp's main(), so a bind to 0.0.0.0 with no token there is not refused and serves without authentication. The host or its process manager owns the bind address, so set ESPN_MCP_AUTH_TOKEN there.

To serve the image over HTTP, pass the token from your shell or an env file (never a fixed value) and name the public host clients use:

PUBLIC_HOST=mcp.example.com   # the host name clients use
export ESPN_MCP_AUTH_TOKEN="$(openssl rand -hex 32)"   # or keep it in an env file
docker run --rm -p 8000:8000 -e ESPN_MCP_AUTH_TOKEN \
  ghcr.io/christianclaudio/mcp-server-espn:latest \
  --transport streamable-http --host 0.0.0.0 --allowed-host "$PUBLIC_HOST"
# with an env file instead: docker run --rm -p 8000:8000 --env-file espn.env ...

📚 Canonical Documentation & Live Doc MCPs

When developing, hardening, or extending MCP servers, consult the official framework and protocol references:

  • FastMCP 4 Framework Reference: https://gofastmcp.com/llms.txt — Server composition (mount), hierarchical middleware, transforms (ToolTransform, ToolSearch), lifespans, and in-memory test clients.

  • Model Context Protocol Specification: https://modelcontextprotocol.io/llms.txt — Official Spec (2026-07-28), wire-level JSON-RPC schemas, annotations, and transport framing.

Live Documentation MCP Endpoints (SSE / Streamable HTTP)

Connect your AI coding agent directly to live documentation servers:

  • FastMCP Documentation Server: https://gofastmcp.com/mcp (Tools: search_fast_mcp, query_docs_filesystem_fast_mcp, submit_feedback)

  • Anthropic MCP Documentation Server: https://modelcontextprotocol.io/mcp (Tools: search_model_context_protocol, query_docs_filesystem_model_context_protocol, submit_feedback)

{
  "mcpServers": {
    "fastmcp-docs": { "type": "sse", "url": "https://gofastmcp.com/mcp" },
    "mcp-official-docs": { "type": "sse", "url": "https://modelcontextprotocol.io/mcp" }
  }
}

🏆 Verification & Quality Gates

# Run unit test suite (100% statement coverage enforced)
pytest

# Static type safety & formatting
mypy --strict src/
ruff check --fix .
ruff format .

# Tool contract, drift & protocol conformance audits
python scripts/check_tool_contract.py
python scripts/check_openapi_drift.py
./scripts/check_conformance.sh

📜 License

Distributed under the Apache-2.0 License.

Available Tools

33 tools
games_get_calendarGames Get CalendarB
Read-onlyIdempotent

Fetch league schedule calendar and active event dates across a season.

Inputs: sport (required), league (required), dates.

games_get_event_oddsGames Get Event OddsB
Read-onlyIdempotent

Fetch sports betting odds, point spreads, over/under, and moneylines across sportsbooks via ESPN Core API.

Inputs: sport (required), league (required), event_id (required), competition_id.

games_get_futuresGames Get FuturesA
Read-onlyIdempotent

Fetch season futures betting markets (championship odds, conference champions, win totals).

Inputs: sport (required), league (required), season.

games_get_game_predictorGames Get Game PredictorB
Read-onlyIdempotent

Fetch ESPN predictive matchup model win percentages, projected margins, and ratings.

Inputs: sport (required), league (required), event_id (required), competition_id.

games_get_game_situationGames Get Game SituationA
Read-onlyIdempotent

Fetch real-time game situation (down, distance, yardline, possession, red zone, clock) via ESPN Core API.

Inputs: sport (required), league (required), event_id (required), competition_id.

games_get_game_summaryGames Get Game SummaryA
Read-onlyIdempotent

Fetch comprehensive game summary for an event ID, including consensus betting lines (spread, moneyline, over/under from DraftKings/Caesars/ESPN BET), matchup predictor (FPI/BPI win probabilities), live win probability curve, season head-to-head series, last 5 games momentum, team statistics, and in-game injuries.

Inputs: sport (required), league (required), event_id (required).

games_get_leaders_by_athleteGames Get Leaders By AthleteB
Read-onlyIdempotent

Fetch statistical leaderboards across a league for individual athletes (e.g. passing yards, rushing, points, strikeouts).

Inputs: sport (required), league (required), sort, limit, +1 more.

games_get_leaders_by_teamGames Get Leaders By TeamB
Read-onlyIdempotent

Fetch team statistical leaderboards across a league (e.g. total offense, defensive points allowed, efficiency).

Inputs: sport (required), league (required), sort, limit, +1 more.

games_get_league_draftGames Get League DraftB
Read-onlyIdempotent

Fetch league draft rounds, team selections, and pick results for a draft year (e.g. the first overall pick).

Inputs: sport (required), league (required), season.

games_get_league_eventsGames Get League EventsA
Read-onlyIdempotent

Fetch the league's current scheduled events. Date filtering is not supported here: for games on a date or range, use games_get_scoreboard with date.

Inputs: sport (required), league (required), dates.

games_get_league_groupsGames Get League GroupsB
Read-onlyIdempotent

Fetch league conference, division, and structural group hierarchies.

Inputs: sport (required), league (required).

games_get_play_by_playGames Get Play By PlayB
Read-onlyIdempotent

Fetch granular play-by-play sequence with clock, downs, distances, yardage, and scoring flags via ESPN Core API.

Inputs: sport (required), league (required), event_id (required), page, +2 more.

games_get_power_indexGames Get Power IndexB
Read-onlyIdempotent

Fetch league team power index (FPI / BPI) ratings and efficiency metrics.

Inputs: sport (required), league (required), season.

games_get_rankingsGames Get RankingsA
Read-onlyIdempotent

Fetch Top 25 national polls and rankings (AP Top 25, Coaches Poll, College Football Playoff rankings) for college sports like NCAAF and NCAAB, including current and previous ranks, votes, and records.

Inputs: sport (required), league (required).

games_get_scoreboardGames Get ScoreboardA
Read-onlyIdempotent

Fetch final scores and results for any date, including postseason games such as the Super Bowl, World Series, or NBA Finals, plus live scores, game status, periods/innings, clocks/outs, TV broadcasts, and probable starters. Returns each game's event ID. Filter by date, week, season type, or Top 25 group. Sports: football, basketball, baseball, hockey, soccer, golf, mma. Use this first to check whether a team played on a particular date; provide the date, sport, and league, and no team ID is needed. Both sport and league are required; for NFL, use sport='football' and league='nfl'. Results are capped by limit (default 50); raise limit on busy dates. For Division I men's college basketball, pass group='50'. Before concluding that a team did not play, check the team's schedule.

Inputs: sport (required), league (required), date, week, +3 more.

games_get_scoreboard_headerGames Get Scoreboard HeaderB
Read-onlyIdempotent

Fetch live ticker scoreboard header data across games for a sport and league.

Inputs: sport, league.

games_get_standingsGames Get StandingsA
Read-onlyIdempotent

Fetch current or historical regular-season division, conference, and league standings (e.g. which team had the best record): win-loss records, win percentages, games back, streaks, and differential. Echoes the season ESPN returned.

Inputs: sport (required), league (required), season.

games_get_team_scheduleGames Get Team ScheduleA
Read-onlyIdempotent

Fetch a team's full season schedule, including past results, upcoming opponents, scores, dates, home/away, and event IDs. Use this for a team's season, last game, or next game; use the scoreboard for games on a particular date. Regular season by default; season_type=3 for postseason.

Inputs: sport (required), league (required), team_id (required), season, +1 more.

games_get_transactionsGames Get TransactionsA
Read-onlyIdempotent

Fetch recent league player transactions (trades, free agent signings, waiver claims, roster activations, and injury reserve designations).

Inputs: sport (required), league (required), limit.

games_get_win_probabilitiesGames Get Win ProbabilitiesC
Read-onlyIdempotent

Fetch high-density win probability timeline curve samples across an entire game.

Inputs: sport (required), league (required), event_id (required), limit, +1 more.

news_get_newsNews Get NewsB
Read-onlyIdempotent

Fetch recent news headlines, injury updates, breaking analysis, and roster moves for a given sport and league.

Inputs: sport (required), league (required), limit.

teams_get_athlete_bioTeams Get Athlete BioB
Read-onlyIdempotent

Fetch detailed athlete biography including birthplace, college, draft round and pick, experience, physical measurements, and background.

Inputs: sport (required), league (required), athlete_id (required).

teams_get_athlete_gamelogTeams Get Athlete GamelogA
Read-onlyIdempotent

Fetch game-by-game statistical performance log for an athlete across an entire season.

Inputs: sport (required), league (required), athlete_id (required), season.

teams_get_athlete_overviewTeams Get Athlete OverviewB
Read-onlyIdempotent

Fetch athlete biographical information, season/career statistical splits, recent individual game logs, rotowire fantasy notes, and next upcoming match.

Inputs: sport (required), league (required), athlete_id (required).

teams_get_athlete_splitsTeams Get Athlete SplitsA
Read-onlyIdempotent

Fetch situational split statistics for an athlete (home vs away, monthly performance, opponents, and win/loss splits).

Inputs: sport (required), league (required), athlete_id (required), season.

teams_get_athlete_statsTeams Get Athlete StatsA
Read-onlyIdempotent

Fetch an athlete's season totals (e.g. a quarterback's passing yards for a season) and career totals and averages. Find the athlete_id with teams_search.

Inputs: sport (required), league (required), athlete_id (required), season.

teams_get_player_statsTeams Get Player StatsA
Read-onlyIdempotent

Extract detailed individual player boxscores and performance metrics for a game (e.g., Strikeouts and Innings Pitched for MLB pitchers; Points, Rebounds, Assists for NBA/WNBA; Passing, Rushing, Receiving for NFL/NCAAF; Goals and Assists for Soccer/NHL).

Inputs: sport (required), league (required), event_id (required).

teams_get_teamTeams Get TeamB
Read-onlyIdempotent

Fetch detailed information for a single team including standing summary, overall record, venue, and next scheduled event.

Inputs: sport (required), league (required), team_id (required).

teams_get_team_depth_chartTeams Get Team Depth ChartB
Read-onlyIdempotent

Fetch team depth chart showing positional starter and backup hierarchies (e.g. QB1, QB2, RB1, RB2) to evaluate starting status and backup substitution impacts.

Inputs: sport (required), league (required), team_id (required).

teams_get_team_rosterTeams Get Team RosterB
Read-onlyIdempotent

Fetch active team roster and injury designations grouped by position, including jersey numbers, experience, position abbreviations, and coaching staff.

Inputs: sport (required), league (required), team_id (required).

teams_get_team_statisticsTeams Get Team StatisticsB
Read-onlyIdempotent

Fetch team and opponent season statistics across offensive, defensive, and special teams categories.

Inputs: sport (required), league (required), team_id (required).

teams_list_teamsTeams List TeamsA
Read-onlyIdempotent

Fetch all active teams in a given sport and league, returning team IDs, names, abbreviations, locations, and colors.

Inputs: sport (required), league (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 33 tools

    Disambiguation3/5

    Most tools target distinct resources, but several clusters overlap: scoreboard vs. league events vs. calendar vs. team schedule, and game summary vs. dedicated odds/predictor/win-probability/play-by-play tools. Athlete bio/overview/stats/gamelog/splits are also related enough to require careful selection, though descriptions generally clarify the intended use.

    Naming Consistency4/5

    Names follow a predictable snake_case domain_action_resource pattern across teams_, games_, and news_ prefixes. Minor deviations exist, such as teams_search omitting 'get' and news_get_news being redundant, but the overall convention is easy to follow.

    Tool Count2/5

    At 33 tools, the surface is heavy for a single MCP server and includes many highly specialized endpoints. While ESPN's broad domain can justify specialization, the count exceeds the typical well-scoped range and increases selection burden.

    Completeness4/5

    Coverage is broad: teams, rosters, schedules, scoreboards, standings, rankings, odds, news, draft, transactions, player stats, game summaries, and live situation data are all represented. A few convenience or aggregate gaps remain, but agents can mostly work around them using related tools.

    Maintenance

    ActivityActive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides access to comprehensive sports data from 5 major leagues (NBA, NFL, MLB, EPL, NHL) including teams, players, games, statistics, standings, injuries, and betting odds through 67+ endpoints. Enables users to query sports information and analytics through natural language.
      12
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Provides AI-powered sports betting intelligence including live odds, injury reports, and documented picks for NBA, NHL, and NCAAB. It enables AI agents to analyze line movements, win rates, and betting edges using real-time data from sportsbettingaianalyzer.com.
      11
      5
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to access comprehensive sports data including football, basketball, American football, and hockey leagues via 11 tools, with no API key required.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables fetching sportsbook odds, live scores, and event information across 70+ books and 30+ leagues, with tools to list sports, get scores, and discover events.
      297 npm
      1
      MIT