io.github.christianclaudio/espn
This MCP server provides AI agents read-only access to live and historical ESPN sports data across games, teams, and news via 33 tools.
Scores & schedules: fetch scoreboards by date/week/season type (including postseason like Super Bowl/NBA Finals), team season schedules, and league calendars/events.
Game analysis: pull full game summaries with betting lines, matchup predictor, momentum, and injuries; play-by-play; live situation (down/distance/red zone); win probability curves; and FPI/BPI power index.
Betting & predictions: get sportsbook odds (spreads, totals, moneylines), consensus lines, futures markets, and predictive win percentages.
Standings & rankings: retrieve division/conference standings with records and streaks, plus Top 25 polls (AP, Coaches, CFP).
League data: access transactions (trades, signings, waivers), statistical leaderboards by athlete and team, draft results, and league group hierarchies.
Teams: list teams, get team detail (venue, record, next event), rosters with injuries and coaches, depth charts, and team/opponent statistics.
Athletes: search by name for IDs, then fetch bio (draft, college, measurements), season/career stats, game logs, situational splits, overview with fantasy notes, and per-game boxscores.
News: retrieve recent headlines, injury updates, and roster moves per sport/league.
Coverage: supports football (NFL/NCAAF), basketball (NBA/WNBA/NCAAB), baseball (MLB), hockey (NHL), and soccer (EPL, MLS, UCL, La Liga, Serie A, Bundesliga, Ligue 1), plus golf and MMA scoreboards.
Deployment: runs via uvx, pip, or Docker over stdio or authenticated Streamable HTTP, with domain profiles (full/games/teams/news/readonly) and optional tool search.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.christianclaudio/espn show me live scores and odds for tonight's NBA games"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🏈 mcp-server-espn
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
Community Project Disclaimermcp-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:
Live Game State & Win Probability: Real-time game events (turnovers, scoring plays, pitching changes) shift momentum and expected outcomes dynamically.
Key Player Injuries & Depth Chart Swaps: An in-game injury or substitution fundamentally alters team efficiency and tactical matchups.
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_*), andespn-news(news_*).Hierarchical Middleware:
Parent:
ParentAuditMiddleware(timing logs, audit trails, and secret scrubbing) andReadOnlyGateMiddleware(fail-closed read-only enforcement).Child:
GamesDomainGuardMiddleware(query limit validation <= 100) andTeamsDomainGuardMiddleware(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/listby 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_toolstakes aquery), or regex patterns with--tool-search-backend regex(ESPN_MCP_TOOL_SEARCH_BACKEND=regex;search_toolstakes apattern).
📈 Sports Intelligence Workflows
Workflow 1: Live In-Game Win Probability & Situation Tracking
Poll Active Games: Agent calls
games_get_scoreboard(sport="football", league="nfl")to identify close games in the 2nd half.Fetch In-Game Situation & Win Probability: Call
games_get_game_situation(sport="football", league="nfl", event_id="401872947")andgames_get_win_probabilities(sport="football", league="nfl", event_id="401872947")to inspect down/distance, red zone state, and live win expectancy curve.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
Bio & Career Context: Call
teams_get_athlete_bio(sport="football", league="nfl", athlete_id="12483")to retrieve draft capital, college pedigree, and physical metrics.Recent Gamelog & Splits: Pull
teams_get_athlete_gamelogandteams_get_athlete_splitsto analyze performance trends against specific defensive schemes and venue conditions.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 |
|
|
| National Football League |
|
|
| NCAA College Football |
|
|
| National Basketball Association |
|
|
| NCAA Men's College Basketball |
|
|
| NCAA Women's Basketball |
|
|
| Women's National Basketball Association |
|
|
| Major League Baseball |
|
|
| National Hockey League |
|
|
| English Premier League |
|
|
| Major League Soccer |
|
|
| UEFA Champions League |
|
|
| Spanish La Liga |
|
|
| Italian Serie A |
|
|
| German Bundesliga |
|
|
| 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 |
|
| Final scores and results for any date ( |
Games |
|
| Consensus betting lines, matchup predictor win %, ATS, scoring plays, drives, leaders, momentum. |
Games |
|
| Season schedule with historical game results and scores: the regular season by default, postseason games with |
Games |
|
| Division, conference, and overall league standings, win-loss records, games back, and win percentages. |
Games |
|
| Top 25 national polls and rankings (AP Top 25, Coaches Poll, College Football Playoff). |
Games |
|
| League-wide transactions, roster trades, waivers, signings, and releases. |
Games |
|
| Statistical leaderboards across players in a league. |
Games |
|
| Team statistical rankings and leaderboards. |
Games |
|
| League conference, division, and structural group hierarchies. |
Games |
|
| The league's current scheduled events. ESPN's events route ignores dates, so date filtering is not supported: a |
Games |
|
| League draft rounds, team selections, and pick results. |
Games |
|
| Live ticker scoreboard header data across games for a sport and league. |
Games |
|
| Sportsbook consensus and provider odds (spreads, totals, moneylines). |
Games |
|
| Play-by-play sequence, clock, scoring, and drive events. |
Games |
|
| Real-time in-game situation (down, distance, yardline, possession, red zone). |
Games |
|
| Live and historical win probability curves across game progression. |
Games |
|
| Pre-game and in-game matchup predictor and projection metrics. |
Games |
|
| League schedule calendar and active event dates across a season. |
Games |
|
| Season futures betting markets (championship odds, win totals). |
Games |
|
| Team power index (FPI / BPI) ratings and efficiency metrics. |
Teams |
|
| Global search for athletes and teams by name/keyword ( |
Teams |
|
| Directory of all franchises/teams in a specified league with IDs, names, and logos. |
Teams |
|
| Team detail overview, venue, record, standings summary, and upcoming scheduled event. |
Teams |
|
| Comprehensive team and opponent statistical category splits (passing, rushing, etc.). |
Teams |
|
| Full active roster grouped by position, coach info, jersey numbers, and injury status. |
Teams |
|
| Positional starter/backup hierarchy (QB1, QB2, etc.) to model injury substitution impacts. |
Teams |
|
| Boxscore statistics for individual athletes across game categories. |
Teams |
|
| Athlete biographical info, season/career stats, game logs, next game, and rotowire notes. |
Teams |
|
| Detailed athlete background, draft history, birth details, college pedigree. |
Teams |
|
| Full seasonal and career category statistics for an athlete. |
Teams |
|
| Game-by-game performance log for an athlete across a season. |
Teams |
|
| Situational statistical splits (home/away, turf/grass, monthly, vs opponents). |
News |
|
| 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-mcpAfter 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-espn3. Run via Docker
docker run --rm -i ghcr.io/christianclaudio/mcp-server-espn:latest🎛️ Engine Configuration
Variable | CLI Flag | Default | Description |
| — |
| Target ESPN REST CDN base URL (bypasses Akamai TLS filter) |
| — |
| HTTP request timeout in seconds |
| — | unset | Shared bearer token required on HTTP transports (stdio ignores it) |
| — | unset |
|
| — |
| Maximum retry attempts on 429 / 5xx with jittered exponential backoff, waiting longer when |
| — |
| Restrict server strictly to read-only inspection tools |
|
|
| Domain sub-server profile: |
|
|
| Replace flat tool catalog with dynamic search transform ( |
|
|
| Tool Search backend: |
🎮 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-mcpAdd 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 8000Connect 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 toolsgames_get_calendarGames Get CalendarBRead-onlyIdempotent
Fetch league schedule calendar and active event dates across a season.
Inputs: sport (required), league (required), dates.
games_get_event_oddsGames Get Event OddsBRead-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 FuturesARead-onlyIdempotent
Fetch season futures betting markets (championship odds, conference champions, win totals).
Inputs: sport (required), league (required), season.
games_get_game_predictorGames Get Game PredictorBRead-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 SituationARead-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 SummaryARead-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 AthleteBRead-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 TeamBRead-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 DraftBRead-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 EventsARead-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 GroupsBRead-onlyIdempotent
Fetch league conference, division, and structural group hierarchies.
Inputs: sport (required), league (required).
games_get_play_by_playGames Get Play By PlayBRead-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 IndexBRead-onlyIdempotent
Fetch league team power index (FPI / BPI) ratings and efficiency metrics.
Inputs: sport (required), league (required), season.
games_get_rankingsGames Get RankingsARead-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 ScoreboardARead-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 HeaderBRead-onlyIdempotent
Fetch live ticker scoreboard header data across games for a sport and league.
Inputs: sport, league.
games_get_standingsGames Get StandingsARead-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 ScheduleARead-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 TransactionsARead-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 ProbabilitiesCRead-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 NewsBRead-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 BioBRead-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 GamelogARead-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 OverviewBRead-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 SplitsARead-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 StatsARead-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 StatsARead-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 TeamBRead-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 ChartBRead-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 RosterBRead-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 StatisticsBRead-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 TeamsARead-onlyIdempotent
Fetch all active teams in a given sport and league, returning team IDs, names, abbreviations, locations, and colors.
Inputs: sport (required), league (required).
teams_searchTeams SearchARead-onlyIdempotent
Search ESPN's entity index by name to find an athlete ID, team ID, or league. Set type='team' for team names such as 'San Francisco 49ers'; type defaults to 'player', so omitting it searches athletes. For a team's games on a particular date, use the scoreboard tool directly when it is available, since it needs no team ID; otherwise use this search for the team ID. Returns IDs and display names for follow-up team or athlete tools.
Inputs: query (required), type, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 33 tools
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.
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.
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.
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
Related MCP Connectors
Live sports stats and pre-computed analysis for AI assistants across NBA, MLB, NFL, and NHL.
Sports odds, player props and source coverage for AI assistants. Connect with your own API key.
NBA, NFL, NHL and combined sports scores as agent tools.
NFL analytics tools for AI agents: stats, fantasy, injuries, schedules, and advanced analysis.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides 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.12MIT
- AlicenseAqualityDmaintenanceProvides 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.115MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access comprehensive sports data including football, basketball, American football, and hockey leagues via 11 tools, with no API key required.MIT
- AlicenseNot gradedqualityCmaintenanceEnables 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 npm1MIT