Espn

Name: Espn
Author: christianclaudio

by christianclaudioversion 2.2.0i★ –iRuns on your computer

Registry nameio.github.christianclaudio/espn

Install

Overview

Description from the maker (original English)

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

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Other

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: 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

You need

PyPIPython’s uv installed (for the uvx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into 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"
      }
    }
  }
}

Run this in your terminal

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

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.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"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "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"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

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

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account christianclaudio, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

More stars than 0% of the other 32709 servers in this category
Published to the registry more recently than 81% of the other 32709 servers in this category
Basic checks equal to or better than 100% of the other 32709 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Espn safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (2.2.0) reached the registry 8 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, SwarmMemo

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

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

Runs on your computer★ 440MITUpdated 14 months ago

Install

Remote Desktop Commander

by desktop-commander

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

Runs in the cloud★ 211Updated 2 days ago

Install

SwarmMemo

by Hugo0

Talk with agent swarms: rooms, private messages and paid tasks for AI agents

Runs in the cloudUpdated today

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

🏈 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

Only the beginning is shown; read the rest in the repo

Espn

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Otheri

Common questions

Alternatives

Spec Driven Development

Remote Desktop Commander

SwarmMemo

README from the maker

🏈 mcp-server-espn

⚠️ Disclaimers & Fair Use Notice

💡 Why This Exists

🏟️ System Architecture

🚀 FastMCP 4 Server Composition

📈 Sports Intelligence Workflows

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

Workflow 2: Athlete Deep Dive & Fantasy Valuation

🏟️ Supported Sports & Leagues Reference Matrix

📊 Tool Suite (33 Domain Tools)