
Connects to ESPN's public site API for live scores, team info, and sports news across multiple leagues without requiring authentication. Part of the Pipeworx gateway system, which offers access to 776+ data sources through a unified interface. You can either call ESPN-specific tools directly or use the ask_pipeworx natural language interface to query sports data without manually constructing API calls. Useful when you need real-time sports information in your Claude workflows without managing API keys or dealing with rate limits. The streamable-http transport means it works through their gateway rather than running locally.
Sponsors
ESPN MCP — keyless multi-sport live scores, teams, and news via ESPN's public site API.
Part of Pipeworx — an MCP gateway connecting AI agents to 1864+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
| Tool | Description |
|---|---|
get_scoreboard | Live sports scores: NFL/NBA/MLB/NHL/soccer/college scores for today's games and results. Returns each game with teams, scores, status (live/final), clock, and period. |
get_teams | List all teams (rosters/franchises) for a league: names, abbreviations, locations, and colors. Works for NFL/NBA/MLB/NHL/soccer/college. |
get_news | Latest sports news headlines for a league: NFL/NBA/MLB/NHL/soccer/college articles with summaries and links. |
get_standings | League standings / table: win-loss records, win %, games behind (and points/draws for soccer), grouped by conference/division. PREFER for "NBA standings", "Premier League table", "NFL division standings", "who is leading ". |
get_team_schedule | A team's schedule — upcoming and recent games with dates, opponents, and (for finished games) scores and result. PREFER for "when do the Lakers play next", "'s schedule", " recent results". Get the numeric team_id from get_teams. |
get_game_summary | A completed or in-progress game's box score: per-player stats by team (e.g. goals/assists/shots for hockey, passing/rushing for football), scoring plays in order, and game leaders (top performer per stat category). PREFER for "box score for ", " vs player stats", "who scored in ". Get the numeric event_id from get_scoreboard or get_team_schedule. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"espn": {
"url": "https://gateway.pipeworx.io/espn/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/espn/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1864+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
curl -X POST https://gateway.pipeworx.io/v1/tools/get_scoreboard \
-H 'Content-Type: application/json' \
-d '{"sport":"football","league":"nfl"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/get_scoreboard. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
@pipeworx/mcp-espn is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/espn/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"espn": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-espn"]
}
}
}
Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Espn data" })
The gateway picks the right tool and fills the arguments automatically.
MIT