Espn

Name: Espn
Author: christianclaudio

作者：christianclaudio版本 2.2.0i★ –i在你的电脑上运行

注册名称io.github.christianclaudio/espn

安装

概览

作者提供的说明（英文原文）

Model Context Protocol server for live & historical sports stats and odds via ESPN.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 其他

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： ESPN_BASE_URL, ESPN_TIMEOUT_SECONDS, ESPN_MAX_RETRIES, ESPN_MCP_READONLY, ESPN_MCP_PROFILE, ESPN_MCP_ENABLE_TOOL_SEARCH, ESPN_MCP_TOOL_SEARCH_BACKEND

你需要

PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": [
        "mcp-server-espn"
      ],
      "env": {
        "ESPN_BASE_URL": "your-value",
        "ESPN_TIMEOUT_SECONDS": "your-value",
        "ESPN_MAX_RETRIES": "your-value",
        "ESPN_MCP_READONLY": "your-value",
        "ESPN_MCP_PROFILE": "your-value",
        "ESPN_MCP_ENABLE_TOOL_SEARCH": "your-value",
        "ESPN_MCP_TOOL_SEARCH_BACKEND": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add espn --env ESPN_BASE_URL=your-value --env ESPN_TIMEOUT_SECONDS=your-value --env ESPN_MAX_RETRIES=your-value --env ESPN_MCP_READONLY=your-value --env ESPN_MCP_PROFILE=your-value --env ESPN_MCP_ENABLE_TOOL_SEARCH=your-value --env ESPN_MCP_TOOL_SEARCH_BACKEND=your-value -- uvx mcp-server-espn

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "espn": {
      "command": "uvx",
      "args": [
        "mcp-server-espn"
      ],
      "env": {
        "ESPN_BASE_URL": "your-value",
        "ESPN_TIMEOUT_SECONDS": "your-value",
        "ESPN_MAX_RETRIES": "your-value",
        "ESPN_MCP_READONLY": "your-value",
        "ESPN_MCP_PROFILE": "your-value",
        "ESPN_MCP_ENABLE_TOOL_SEARCH": "your-value",
        "ESPN_MCP_TOOL_SEARCH_BACKEND": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "espn": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-espn"
      ],
      "env": {
        "ESPN_BASE_URL": "your-value",
        "ESPN_TIMEOUT_SECONDS": "your-value",
        "ESPN_MAX_RETRIES": "your-value",
        "ESPN_MCP_READONLY": "your-value",
        "ESPN_MCP_PROFILE": "your-value",
        "ESPN_MCP_ENABLE_TOOL_SEARCH": "your-value",
        "ESPN_MCP_TOOL_SEARCH_BACKEND": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

ESPN_BASE_URL env
Optional REST base URL override
ESPN_TIMEOUT_SECONDS env
HTTP request timeout in seconds
ESPN_MAX_RETRIES env
Maximum retry attempts on HTTP 429 / 5xx
ESPN_MCP_READONLY env
Restrict server execution strictly to read-only inspection tools
ESPN_MCP_PROFILE env
Server domain profile (full, games, teams, news, readonly)
ESPN_MCP_ENABLE_TOOL_SEARCH env
Replace flat tool catalog with dynamic search transform
ESPN_MCP_TOOL_SEARCH_BACKEND env
Tool Search backend: bm25 (default) or regex

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 christianclaudio 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32712 个服务器的 0%
发布到注册中心的时间比此分类中其他 32712 个服务器的 81% 更新
基础检查结果等于或优于此分类中其他 32712 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Espn 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（2.2.0）于8天前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, Aiterm MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211前天更新

安装

Aiterm MCP

作者：kitepon

Persistent terminals and one launcher for Claude, Codex, Grok, Cursor, and Antigravity harnesses.

在你的电脑上运行今天更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

🏈 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

[!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.

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

🚀 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

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") and games_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_gamelog and teams_get_athlete_splits to 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
`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

只显示了开头部分；其余内容请在仓库中阅读