Provides tools for accessing league data stored in Supabase, including context tools like assess_league_readiness, query_leagues, and get_league_context.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AltSportsLeagues MCP Server Find trending alternative sports leagues in Europe"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP-compatible server for the AltSportsLeagues platform — league discovery, valuation, market intelligence, fingerprinting, onboarding pipeline visibility, and time-series market data for AI agents and sportsbooks.
# Install
pip install altsportsleagues-mcp
# Run (stdio)
ALTSPORTSLEAGUES_API_KEY=your_key altsportsleagues-mcp
# Run (HTTP/SSE)
ALTSPORTSLEAGUES_API_KEY=your_key altsportsleagues-mcp --sse --port 8080Related MCP server: SportsQuant MCP Server
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"altsportsleagues": {
"command": "altsportsleagues-mcp",
"env": {
"ALTSPORTSLEAGUES_API_KEY": "your_api_key",
"SUPABASE_SERVICE_ROLE_KEY": "your_supabase_key"
}
}
}
}Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"altsportsleagues": {
"command": "altsportsleagues-mcp",
"env": {
"ALTSPORTSLEAGUES_API_KEY": "your_api_key",
"SUPABASE_SERVICE_ROLE_KEY": "your_supabase_key"
}
}
}
}mcp:
servers:
altsportsleagues:
command: altsportsleagues-mcp
env:
ALTSPORTSLEAGUES_API_KEY: your_api_key
SUPABASE_SERVICE_ROLE_KEY: your_supabase_keynpx altsportsleagues-mcpVariable | Required | Description |
| Yes | Your AltSportsLeagues API key |
| No | Override API base URL (default: https://api.altsportsleagues.ai) |
| No | Supabase project URL (for context tools) |
| No | Supabase service role key (for context tools) |
Tool | Description |
| AI-powered search for alternative sports leagues |
| Deep-research a specific league |
| List all previously discovered leagues |
| Identify underserved market opportunities |
| Aggregate discovery pipeline statistics |
| Trending sports and regions |
Tool | Description |
| Multi-dimensional league evaluation and tier assignment |
| Tier classification system definitions |
| Score a potential partnership opportunity |
| Qualification decision matrix |
Tool | Description |
| Generate a unique DNA profile for a league |
| Retrieve an existing fingerprint profile |
| Find leagues with similar profiles |
| Check fingerprint quality and completeness |
Tool | Description |
| Questionnaire processing status |
| League onboarding pipeline progress |
| Full pipeline stage-by-stage breakdown |
| Aggregate onboarding statistics |
Tool | Description |
| Full readiness report with composite score |
| Classify into 5 canonical archetypes |
| Sport-specific edge cases for betting markets |
| Trading anomaly and integrity risk detection |
| Maturity and production readiness ranking |
| Schema alignment check against ASD canonical schema |
| 5-dimension readiness assessment via Supabase |
Tool | Description |
| Complete intelligence context assembly |
| Side-by-side multi-league comparison |
| Flexible league search with filters |
| All uploaded documents for a league |
| Scraped-vs-verified field coverage analysis |
Tool | Description |
| Historical valuation snapshots |
| SEC 10-Q style quarterly report |
| Top movers and decliners |
| Aggregate market index |
| Head-to-head trajectory comparison |
MIT
Assess a league's readiness across 5 dimensions using live Supabase data.
Queries the league record directly and computes scores for: Data Readiness (25%) -- profile field completeness, API availability, social presence. Technical Readiness (20%) -- API quality, schema alignment. Business Readiness (20%) -- reach, broadcast partners, social following. Operational Readiness (20%) -- event cadence, roster depth. Market Readiness (15%) -- opportunity score, priority score.
Returns an overall score, certification eligibility (premium / standard / provisional / not_eligible), per-dimension breakdowns, and specific recommendations for improvement.
Inputs: league_id (required), assessment_type. Returns: object
Check the quality and completeness of a league's fingerprint.
Analyzes which fingerprint dimensions are well-populated vs sparse, identifies data gaps that could improve the profile, and returns an overall quality score with recommendations for enrichment.
Inputs: league_id (required). Returns: object
Classify a sport into one of 5 canonical archetypes.
The 5 archetypes are: Combat (MMA, boxing), Racing (F1, NASCAR), Action/Heat (surfing, skateboarding), Precision (golf, darts), and Team (lacrosse, rugby). Each archetype has distinct edge cases, betting market structures, and data requirements.
Returns the archetype classification, confidence level, key characteristics, and sport-specific edge cases to watch for.
Inputs: sport_type (required), league_name. Returns: object
Side-by-side comparison of multiple leagues.
Takes a list of league UUIDs and returns a comparison table with each league's name, sport type, archetype, tier, readiness score, onboarding stage, scores, data coverage percentage, data origin (scraped/verified), latest valuation score, score change, growth trajectory, and latest quarter.
Use this when evaluating multiple partnership candidates or benchmarking leagues within a sport vertical.
Inputs: league_ids (required). Returns: object
Head-to-head valuation trajectory comparison between two leagues.
Returns side-by-side score histories showing how both leagues' valuations have evolved over recent quarters. Highlights diverging or converging trends, total change over the period, and current growth trajectories.
Use this when a user asks "how does League A compare to League B over time?" or wants to evaluate two partnership candidates.
Inputs: league_id_1 (required), league_id_2 (required). Returns: object
Detect potential trading anomalies and integrity risks for a sport.
Analyzes a sport type for known anomaly patterns: suspicious odds movements, market suspension triggers, data feed gaps, timing irregularities, and result manipulation indicators.
Returns anomaly patterns, suggested alert rules, and an overall risk score.
Inputs: sport_type (required), api_url. Returns: object
Search for alternative sports leagues using AI-powered discovery.
Accepts natural language queries like "combat sports in Southeast Asia" or "emerging racing leagues." Optionally pass structured filters for sport type, region, minimum fan count, etc.
Returns a ranked list of matching leagues with summary profiles.
Inputs: query (required), filters. Returns: object
Evaluate a league's value across multiple dimensions and assign a tier.
Runs the full valuation model: Market Potential (25%), Data Quality (20%), Betting Readiness (20%), Fan Engagement (15%), Operational Maturity (10%), and Risk Deductions (10%). Produces a 0-1000 composite score and an ASD Certificate Tier (1.1 through 4.9).
Optionally pass custom criteria weights or overrides.
Inputs: league_id (required), criteria. Returns: object
Generate a unique fingerprint profile for a league.
Creates a multi-dimensional DNA profile capturing the league's sport archetype characteristics, data coverage, market positioning, fan demographics, operational maturity, and competitive landscape. The fingerprint enables similarity search and clustering.
Set force=True to regenerate even if a fingerprint already exists.
Inputs: league_id (required), force. Returns: object
Generate a full readiness report for a league.
Combines API valuation results, sportsbook preference scoring, and questionnaire completeness into a single 0-1000 composite score across 6 weighted dimensions: Market Potential (25%, max 250), Data Quality (20%, max 200), Betting Readiness (20%, max 200), Fan Engagement (15%, max 150), Operational Maturity (10%, max 100), Risk Deductions (10%, max 100).
Returns the composite score, per-dimension breakdown, ASD Certificate Tier (1.1-4.9), value-vs-friction classification (fast-track / invest / pass), and actionable recommendations.
Inputs: league_id (required). Returns: object
Get a detailed scraped-vs-verified field map for a league.
Analyzes every profile field to show which are populated vs empty, and classifies the data origin (scraped / verified / unknown). Returns a per-field breakdown with value previews and an aggregate coverage percentage. Useful for understanding data confidence and identifying what still needs verification.
Inputs: league_id (required). Returns: object
Get aggregate statistics about the discovery pipeline.
Returns total leagues discovered, breakdown by sport type and region, discovery velocity, and coverage metrics. No parameters needed.
Inputs: no named parameters. Returns: object
Retrieve the existing fingerprint profile for a league.
Returns the full fingerprint with archetype classification, dimensional scores, characteristic tags, and metadata. Returns an error if no fingerprint has been generated yet (use generate_fingerprint first).
Inputs: league_id (required). Returns: object
Check how well a league's API aligns with ASD's canonical kb_catalog schema.
Probes the league's API and maps its data structures against the ASD canonical schema (WHO x WHEN x WHAT x HISTORY). Returns coverage score, matched schemas, missing schemas, data gaps, and an integration complexity estimate (simple / moderate / complex / custom).
Inputs: api_url (required), league_name. Returns: object
Assemble the complete intelligence context for a league.
This is the primary "tell me everything" tool. Pulls the full league record, scores, recent valuation snapshots, and computes a scraped-vs- verified data coverage analysis. Returns all data needed for deep reasoning about a league's current state, readiness, and potential.
Includes: core profile, all scores, enrichment data, sport archetype, tier, onboarding stage, discovery classification, verification status, and the last 4 valuation snapshots.
Inputs: league_id (required). Returns: object
Get all uploaded documents for a league.
Returns metadata for all documents associated with the league: PDFs, compliance documents, API specification files, questionnaire responses, financial statements, etc. Includes document type, upload date, file size, and processing status.
Inputs: league_id (required). Returns: object
Retrieve the aggregate league market index -- a stock-market-style summary.
Returns total league count, per-archetype averages (avg valuation, avg score change), top movers, and top decliners. Optionally filter by sport archetype (combat, racing, action_heat, precision, team).
Use this to get a birds-eye view of the entire league marketplace, or drill into a specific sport archetype vertical.
Inputs: archetype. Returns: object
Retrieve the top movers and decliners across all leagues.
Returns leagues ranked by recent score change -- the biggest gainers and biggest losers. Each entry includes the league name, sport archetype, current valuation score, score change, growth trajectory, and momentum classification (rapid_expansion, strong_growth, steady, declining).
Use this to find which leagues are trending up or down right now. No parameters required -- returns the current market-wide movers.
Inputs: no named parameters. Returns: object
Retrieve an SEC 10-Q style quarterly report for a league.
Returns the full valuation breakdown for a specific quarter: composite score (0-100), 6 dimension scores, financials (sponsorship totals, contract totals, projected revenue), quarter-over-quarter growth rates, social signals, demographics, upcoming events, seasonality phase, executive summary, key highlights, risk factors, forward guidance, recommended action, and data confidence.
If no quarter is specified, returns the latest available report.
Inputs: league_id (required), quarter. Returns: object
Retrieve historical valuation snapshots for a league -- like a stock price chart.
Returns a time series of valuation scores across 6 weighted dimensions (Social Growth 25%, Contract Values 20%, Sponsorship Revenue 20%, Events Impact 15%, Seasonality 10%, Demographics 10%).
Each snapshot includes the composite score, per-dimension breakdowns, score change from previous period, growth trajectory classification, and data confidence level.
Use this to understand how a league's value has changed over time.
Inputs: league_id (required), limit. Returns: object
Identify current market opportunities across sports verticals.
Returns a breakdown of underserved sport types, high-demand regions, and gaps where sportsbook demand exceeds available league supply. No parameters needed.
Inputs: no named parameters. Returns: object
Get onboarding pipeline progress for a specific league.
Returns the league's current onboarding stage (discovered, contacted, questionnaire_sent, questionnaire_received, under_review, certified, live), time-in-stage, completed steps, blocking items, and next actions required.
Inputs: league_id (required). Returns: object
Get aggregate statistics about the onboarding pipeline.
Returns total leagues onboarded, conversion rates by stage, average time-to-certification, success rates by sport archetype, and month-over-month trends. No parameters needed.
Inputs: no named parameters. Returns: object
Get an overview of all leagues currently in the onboarding pipeline.
Returns a stage-by-stage breakdown showing how many leagues are at each onboarding stage, average time-in-stage, bottlenecks, and recently progressed leagues. No parameters needed.
Inputs: no named parameters. Returns: object
Get the qualification decision matrix for league assessment.
Returns the full decision matrix that maps league attributes to qualification outcomes: fast-track, invest, monitor, or pass. Includes dimension thresholds, weighting logic, and tier boundaries. No parameters needed.
Inputs: no named parameters. Returns: object
Get the processing status of a submitted league questionnaire.
Returns the current state of a questionnaire submission: received, processing, completed, or error. Includes section-level completion percentages and confidence tiers per field (manual / RAG / AI).
Inputs: questionnaire_id (required). Returns: object
Get the tier classification system definitions and criteria.
Returns all tier levels (T0 Elite through T4 Enterprise CV) with their score thresholds, contract value ranges, pricing flavors (FRIENDLY/DEAL/STICK/RETAIL), and qualifying criteria. No parameters needed.
Inputs: no named parameters. Returns: object
Get trending sports and regions where new leagues are being discovered.
Returns emerging sport types gaining traction, geographic hotspots with accelerating league creation, and recent discovery highlights. No parameters needed.
Inputs: no named parameters. Returns: object
Identify sport-specific edge cases that affect betting market integrity.
Analyzes a sport type for known edge cases: race delays, no contests, weather disruptions, disqualifications, judging controversies, injury stoppages, etc. Each edge case includes severity, frequency, affected betting markets, and mitigation strategies.
Optionally filter by specific market types (H2H, props, futures, etc.).
Inputs: sport_type (required), market_preferences. Returns: object
List all previously discovered leagues in the AltSportsLeagues database.
Returns paginated league summaries ordered by discovery date. Use this to browse what has already been found before running new searches.
Inputs: limit, offset. Returns: object
Query and filter leagues from the database.
Flexible search across all leagues with smart filters. Combine any filters to narrow results. Returns league summaries sorted by most recently updated.
Filter options:
sport_archetype: combat, racing, action_heat, precision, team
tier_range: e.g. "1.0-2.9" for Tier 1-2 leagues
verification_status: "verified" or "unverified"
search: free-text search across league name and sport type
Inputs: sport_archetype, tier_range, verification_status, search, +1 more. Returns: object
Rank a league's maturity and production readiness.
Takes key league metrics and produces a maturity assessment: overall maturity score, letter grade (A-F), production readiness level, and market position tier (Tier 1-4). Useful for prioritizing which leagues to onboard first.
Inputs: league_name (required), api_score (required), schema_alignment (required), sport_type (required). Returns: object
Deep-research a specific league to gather comprehensive intelligence.
Takes a league name (and optionally its sport and website) and runs an AI research pipeline: web scraping, social media analysis, news coverage, competitive landscape, and data availability assessment.
Returns a detailed intelligence dossier suitable for evaluation.
Inputs: league_name (required), sport, website. Returns: object
Score a potential partnership opportunity with a league.
Evaluates how well a league fits as a partnership candidate based on data quality, market demand, sportsbook interest, integration complexity, and revenue potential. Returns a multi-factor partnership score with recommendations.
Inputs: league_id (required), parameters. Returns: object
Find leagues with similar fingerprint profiles.
Uses the league's fingerprint to search for the most similar leagues by archetype, operational maturity, market positioning, and data characteristics. Useful for benchmarking, competitive analysis, and finding comparable partnership candidates.
Inputs: league_id (required), limit. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 35 tools
Most tools have distinct purposes, but there is overlap between assess_league_readiness, evaluate_league, and generate_readiness_report, all of which compute readiness scores. Similarly, compare_leagues and compare_league_trajectories could be confused. However, the descriptions help differentiate them.
All tool names follow a consistent snake_case verb_noun pattern (e.g., assess_league_readiness, get_data_coverage). Naming conventions are uniform and predictable, aiding an agent in understanding the tool's action and object.
With 35 tools, the server feels overloaded. While each tool serves a specific purpose, the number is high for the domain, potentially overwhelming an agent. The scope is broad, but many tools could be consolidated (e.g., multiple readiness/valuation tools).
The tool set covers discovery, evaluation, fingerprinting, pipeline management, comparisons, anomaly detection, and market analysis. Missing are tools for direct data ingestion or modification of league records, but the server focuses on analysis rather than CRUD operations, so this is acceptable.
Sports prediction markets for AI agents — live prices, quotes, orders, and positions.
Grounded sports predictions plus European soccer and tennis arbitrage data for AI agents.
Agent-native sports token network. 1,435 tokens across 98 sports, 9 global regions.
Live sports stats and pre-computed analysis for AI assistants across NBA, MLB, NFL, and NHL.
