sportsdata-mcp
An MCP server that exposes sports-data APIs from multiple providers (AFL, Sportsbet, Entain, NRL) as interchangeable tools, enabling cross-provider odds and stats comparison.
README
sportsdata-mcp
An MCP server that exposes sports-data APIs (bookmakers, league/governing-body feeds, aggregators) as tools, configurable so you only load the tool groups you need. A capability-tag system makes tools from different providers interchangeable wherever they answer the same question — so the model can compare odds across bookies or stats across data sources with one discovery call.
Five providers ship today — AFL (api.afl.com.au), Sportsbet,
Entain / Ladbrokes, NRL (mc.championdata.com) and NBA
(cdn.nba.com + stats.nba.com) — exposing 112 provider tools across 17
groups, plus 3 always-on meta-tools. New providers are added by dropping a YAML
spec into src/sportsdata_mcp/specs/; the engine needs no code changes.
Design notes and roadmap live in
PLAN.md.
Install
uvx sportsdata-mcp serve # run without installing
# or
pip install sportsdata-mcp
Quickstart
sportsdata-mcp version # print version info
sportsdata-mcp list-groups # see every available tool group
sportsdata-mcp lint # validate the packaged specs
sportsdata-mcp doctor # probe enabled groups for reachability + auth
sportsdata-mcp serve # start the MCP stdio server (default command)
Enable tool groups with a config file or the SPORTSDATA_MCP_GROUPS env var:
SPORTSDATA_MCP_GROUPS="afl.public.core,sportsbet.racing,entain.graphql" sportsdata-mcp serve
See examples/ for Claude Desktop / Claude Code config snippets
and a worked cross-bookie odds-comparison prompt.
Configuration
Config is resolved in this order (first hit wins):
--config <path>flag$SPORTSDATA_MCP_CONFIG./sportsdata-mcp.yaml~/.config/sportsdata-mcp/config.yaml- built-in defaults
# sportsdata-mcp.yaml
enabled_groups:
- afl.public.core
- sportsbet.racing
- entain.graphql
providers: # all optional; sensible defaults apply
sportsbet:
request_timeout_seconds: 30
rate_limit_rps: 10 # sustained requests/sec (token bucket)
max_response_bytes: 0 # 0 = no cap (default); set a positive byte count to guard context
secrets: {} # for authenticated providers; prefer env vars in prod
Environment variables
| Variable | Effect |
|---|---|
SPORTSDATA_MCP_GROUPS |
Comma-separated group list; overrides enabled_groups. |
SPORTSDATA_MCP_CONFIG |
Path to a config file (see resolution order above). |
SPORTSDATA_MCP_MAX_BYTES |
Global response-size cap in bytes for every provider that doesn't set its own max_response_bytes. 0 (the default) means no cap. |
Meta-tools (list_available_groups, list_tools_by_capability, list_resources)
are always registered regardless of what is enabled, so a fresh install can still
guide the model to turn groups on.
On the response-size cap. There is no cap by default — every tool returns
whatever the upstream API sends. If you want to guard the model's context window you
can opt in to a cap: precedence is providers.<id>.max_response_bytes >
SPORTSDATA_MCP_MAX_BYTES > the default (0, unlimited). Be aware that very large
payloads (e.g. Sportsbet's full *_event_markets firehose, ~2 MB) won't fit in
Claude's ~200 K-token context regardless — for those, prefer a narrower tool such as
sportsbet_sports_card with includeTopMarkets: true.
Tool groups
Run sportsdata-mcp list-groups for live counts and descriptions.
AFL — api.afl.com.au
| Group | Tools | Notes |
|---|---|---|
afl.public.core |
22 | Competitions, seasons, rounds, fixtures, ladders, match stats |
afl.public.broadcasting |
9 | Broadcast regions, guides, providers |
afl.public.content |
8 | News/articles, videos, photos |
afl.premium.cfs |
1 | CFS premium ops — needs the anonymous x-media-mis-token |
afl.premium.statspro |
1 | StatsPro ops — needs the x-media-mis-token |
afl.premium.keyserver |
1 | HLS video URL signing |
Sportsbet — sportsbet.com.au
| Group | Tools | Notes |
|---|---|---|
sportsbet.racing |
15 | Race meetings, racecards, results, futures, SRMs |
sportsbet.sports |
14 | Sport events, markets, prices, SGMs |
sportsbet.cross |
12 | Live status, commentary, ladders, promos, video |
sportsbet.results |
2 | Resulted events by date |
sportsbet.graphql |
1 | Persisted GraphQL gateway (apigw/sportsbook/graph) |
Entain / Ladbrokes — ladbrokes.com.au
| Group | Tools | Notes |
|---|---|---|
entain.rest |
13 | Navigation quick-links and REST surfaces |
entain.graphql |
1 | 127 persisted GraphQL ops (gql/router) |
entain.cdn |
1 | Contentful CMS entries (promotions, major-event nav) |
NRL — mc.championdata.com
| Group | Tools | Notes |
|---|---|---|
nrl.public.core |
4 | Champion Data match centre: competitions, fixture, per-match player stats, app settings |
Plus the nrl://stats/definitions resource (dictionary of every NRL stat code).
NBA — cdn.nba.com + stats.nba.com
| Group | Tools | Notes |
|---|---|---|
nba.public.cdn |
5 | Open CDN JSON: today's scoreboard, full schedule, live box score + play-by-play, odds |
nba.stats |
2 | nba_daily_lineups + nba_stats_call, the dispatcher over the 137-endpoint /stats/ API |
nba_stats_call fronts the whole stats.nba.com /stats/ analytics surface (player/team
dashboards, box scores v2+v3, shot charts, play-by-play, leaders, standings, draft, hustle,
tracking, …). Browse every operation, its required params and its defaults in the
nba://stats/operations resource.
Cross-provider comparison
Every tool is tagged with provider-agnostic capability slugs (e.g.
sport.event_markets, racing.race_card). Tools sharing a slug answer the same
question and are directly comparable across providers. The discovery flow:
list_tools_by_capability("sport.event_markets")→ every enabled tool exposing it- Call each provider's tool concurrently with the resolved event ids
- Compare the raw snapshots (schemas are not normalised — the model reconciles them)
See examples/comparator-prompt.md for a full
"compare Storm v Cowboys odds across bookies" walkthrough.
Per-provider notes
- Sportsbet — anonymous public APIs; no secrets needed. REST events are keyed
by integer
eventId; a persisted-GraphQL gateway is exposed viasportsbet_graphql_call(browsesportsbet://graphql/operations). - Entain / Ladbrokes — a persisted-GraphQL gateway; the model supplies an
operation name + variables (discover them in
entain://graphql/operations). Hashes can drift when the front-end bundle ships; refresh them withsportsdata-mcp refresh-hashes entain. - AFL —
afl.public.*is anonymous.afl.premium.*mints an anonymousx-media-mis-tokenautomatically; some premium endpoints still return 401 for anonymous callers. - NRL — the anonymous Champion Data match-centre CDN (
mc.championdata.com), the same static JSON the official nrl.com match centre reads. No secrets, no cache-buster params needed. Resolve acompetitionIdfromnrl_competitions(e.g. 12999 = 2026 NRL Premiership), amatchIdfromnrl_fixture, then pull per-player match stats fromnrl_match; decode stat codes vianrl://stats/definitions. - NBA — two surfaces, no secrets.
cdn.nba.comis wide open (it even serves JSON astext/plain, which the client accepts).stats.nba.comsits behind Akamai, which black-holes any request missing a full browser header bundle — the spec ships that bundle inprovider.default_headers, so it just works. Akamai also rate-limits hard, so the spec'sdefaultsblock throttles NBA to ~1 req/2.5 s, sets a 45 s timeout, and retries transient429/5xxwith exponential backoff (all overridable viaproviders.nba.*). The/stats/family is one dispatcher (nba_stats_call): pick anoperation(the path segment, e.g.leaguedashplayerstats) and passquery_params— each operation already carries NBA's full default param set, so you override only what matters. Most responses are column-oriented (resultSets:[{name, headers, rowSet}]}); v3 box scores are nested.
CLI reference
| Command | Purpose |
|---|---|
serve |
Start the MCP stdio server (default when no subcommand) |
list-groups |
Print every group with tool count + description |
lint |
Validate specs against the schema + capability catalogue (nonzero on failure) |
doctor |
Per-provider reachability + auth + REST-contract probe (nonzero on failure) |
refresh-hashes <provider> |
Refresh persisted-query hashes from the live front-end bundle (--dry-run to preview) |
version |
Print version info |
-v / --verbose enables DEBUG logging (and un-silences httpx/httpcore).
Contributing
Adding a provider is a spec-only change in the common case:
- Write
src/sportsdata_mcp/specs/<provider>.yaml(copy an existing spec). - Tag each tool with capability slugs from
specs/_capabilities.yaml; add a new slug there if none fits (two providers sharing a slug makes them comparable). sportsdata-mcp lint— must pass.sportsdata-mcp doctor(with the new groups enabled) — probes it live.pytest -m "not live"— offline suite; drop the marker filter to run live tests.
pip install -e ".[dev]"
pytest -m "not live"
ruff check .
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.