Skip to main content
Glama
SportScore

SportScore

by Backspace-me

sportscore-mcp

MCP server for SportScore — live scores, match details, standings, top scorers, brackets and player stats across football, basketball, cricket and tennis. Free public API, CORS-open, no API key.

Backspace-me/sportscore-mcp MCP server

Works in any Model Context Protocol host: Claude Desktop, Cursor, Continue, Zed, and custom MCP clients.

What it gives your AI assistant

  • Live + recent matches by sport

  • Single match detail (score, status, timeline, lineups)

  • Team schedules

  • League / competition standings

  • Top scorers / top assisters

  • Player statistics and metadata

  • Knockout tournament brackets

  • Live match tracker data

Related MCP server: mcp-odds-api

Install in Claude Desktop

Add this to claude_desktop_config.json:

macOS — ~/Library/Application Support/Claude/claude_desktop_config.json Windows — %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sportscore": {
      "command": "npx",
      "args": ["-y", "sportscore-mcp"]
    }
  }
}

Restart Claude Desktop. You should see the SportScore tools in the tools menu. Ask things like:

  • "What Premier League matches are live right now?"

  • "Show me the NBA standings."

  • "Who are the top scorers in La Liga?"

  • "What's Barcelona's next fixture?"

Install in Cursor / Continue / Zed

Any MCP host that accepts a stdio command works. The npx -y sportscore-mcp invocation is the same — consult your host's MCP docs for the exact config file.

Configuration

Environment variables (optional):

Variable

Default

Purpose

SPORTSCORE_API_BASE

https://sportscore.com

Override the API base URL (useful for staging / self-hosted)

SPORTSCORE_UA

sportscore-mcp/0.3 (+https://sportscore.com/developers/)

Override the User-Agent string

SPORTSCORE_HTTP_PORT

(unset)

If set, run as a Streamable HTTP server on this port instead of stdio

SPORTSCORE_HTTP_HOST

127.0.0.1

Bind address when running in HTTP mode

SPORTSCORE_NO_TELEMETRY

(unset)

Set to 1 to disable the opt-out install-ping (see below)

Anonymous install-ping (opt-out)

On startup the server fires one fire-and-forget POST to https://sportscore.com/api/mcp/ping/ with this payload:

{ "client": "sportscore-mcp", "version": "0.3.0", "transport": "stdio", "host": "darwin", "node": "20.11.0" }

That's the whole payload — no user id, no IP, no cookies, no fingerprint. We use it to see rough weekly-active-installs and Node/OS spread so we know what to support. Opt out with SPORTSCORE_NO_TELEMETRY=1.

Tools

Tool

Purpose

Required args

get_matches

Live + recent matches

sport

get_match_detail

Single match by slug

sport, slug

get_team_schedule

Team fixtures

sport, slug

get_standings

League table

sport, slug

get_top_scorers

Top scorers / assisters

sport, slug

get_player

Player stats

sport, slug

get_bracket

Knockout bracket

sport, slug

get_tracker

Live tracker data

sport, id

Full parameter docs and response shapes: sportscore.com/developers/ · OpenAPI 3.0 spec

Attribution

This MCP server surfaces a Powered by SportScore attribution with every tool result. The free-tier API requires that attribution to remain visible in end-user-facing output — so please don't strip it from your prompts or post-processing.

Commercial / white-label use that needs to remove the attribution: api@sportscore.com. Terms: sportscore.com/developers/terms/.

Rate limits

Free tier: approximately 1000 requests / 24h / IP, with 60-second edge caching. Sensible for any MCP workflow — a user driving a chat session will not approach the limit. Bulk / production / higher-volume use: contact api@sportscore.com.

License

MIT — see LICENSE.

Available Tools

8 tools
get_bracketA

Get the knockout bracket for a tournament (e.g. 'uefa-champions-league', 'nba-playoffs').

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

get_match_detailA

Get detailed data for a single match by its slug (e.g. 'manchester-united-vs-liverpool'): score, status, timeline, lineups. Slugs come from get_matches results or match URLs on sportscore.com.

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

get_matchesA

List live and recent matches for a sport. Returns up to limit matches with scores, status, kickoff time and team logos. Good default for 'what's happening in football right now?'.

Inputs: sport (required), limit.

get_playerA

Get player statistics and metadata by player slug (e.g. 'lionel-messi', 'lebron-james', 'virat-kohli').

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

get_standingsA

Get the current standings table for a league or competition by slug (e.g. 'premier-league', 'la-liga', 'nba').

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

get_team_scheduleA

Get a team's past and upcoming fixtures by team slug (e.g. 'barcelona', 'manchester-united', 'los-angeles-lakers').

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

get_top_scorersA

Get the top scorers (or top assisters) for a competition. Useful for 'who's leading the Premier League scoring charts?'.

Inputs: slug (required), sport (required), stat, limit.

get_trackerA

Get live match tracker data (position, animation frames) for a match by numeric id. Usually only useful for football.

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

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of sports data (brackets, match detail, list matches, players, standings, schedule, top scorers, live tracker) with no overlapping purposes. The descriptions clearly differentiate them.

    Naming Consistency5/5

    All tool names follow a consistent `get_` prefix followed by a descriptive noun in snake_case (e.g., get_bracket, get_match_detail). The pattern is uniform and predictable.

    Tool Count5/5

    With 8 tools, the server covers a broad range of common sports queries without being excessive or insufficient. Each tool has a clear role, making the set well-scoped for its domain.

    Completeness4/5

    The tools cover core sports data needs: matches, details, standings, schedules, players, top scorers, brackets, and live tracking. A minor gap is the lack of team or league metadata tools, but the surface is largely complete for typical use cases.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    • Sleeper MCP server for ChatGPT, Claude and any AI agent: set lineup, submit waiver claim, propose trade, answer trade offer, send league message, list matchups and list free agents in your own Sleeper account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Sleeper yourself; Cotlet does not store your password and you need no Sleeper API key. About the official Sleeper API: Sleeper has only a limited API (checked 28 Oct 2026). Its public API is read-only and needs no token: it returns users, leagues, rosters, matchups, transactions and drafts, and it cannot set a lineup, place a waiver claim, propose a trade or post in league chat. Setup and FAQ: https://cotlet.dev/integrations/sleeper-api-mcp-server

      https://cotlet.dev/mcp/v1/sleeper
    • An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.

      https://mcp.manifoldmcp.com/mcp
    • Strava MCP server for ChatGPT, Claude and any AI agent: list activities, update activity gear, read club leaderboard, comment on activity, log manual activity and request account export in your own Strava account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Strava yourself; Cotlet does not store your password and you need no Strava API key. About the official Strava API: Strava has an official API and, since 1 June 2026, an official MCP connector (checked 27 Oct 2026). The MCP is read-only, works with Claude only and needs a paid Strava subscription. Setup and FAQ: https://cotlet.dev/integrations/strava-api-mcp-server

      https://cotlet.dev/mcp/v1/strava
    • WHOOP MCP server for ChatGPT, Claude and any AI agent: get day summary, list recoveries, list sleeps, list workouts, list cycles and get membership in your own WHOOP account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to WHOOP yourself; Cotlet does not store your password and you need no WHOOP API key. About the official WHOOP API: WHOOP has an official developer API (v2, OAuth 2.0, read-only) but no official MCP server (checked 27 Oct 2026). The API returns recovery, sleep, cycles and workouts to an app you register in the WHOOP Developer Dashboard, and an app WHOOP has not approved serves 10 members. Setup and FAQ: https://cotlet.dev/integrations/whoop-api-mcp-server

      https://cotlet.dev/mcp/v1/whoop

    Related MCP Servers

    • 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.
      108 npm
      1
      MIT
    • F
      license
      B
      quality
      D
      maintenance
      MCP server that enables Claude Desktop to access real-time sports data including live scores, fixtures, standings, and NBA statistics using free APIs.
      10
      -
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for the FootballStack football data API. Gives LLM clients and AI agents (Claude, Cursor) access to real football data — fixtures, standings, lineups, live events, shot-level xG with pitch coordinates, and model-derived fair odds.
      12
      MIT