{"slug": "show-hn-lumify-sports-intelligence-api-for-agents-try-without-signup", "title": "Show HN: Lumify – sports intelligence API for agents (try without signup)", "summary": "Lumify, a sports intelligence API designed for AI agents, launched with MCP tools, REST/SDK support, and a no-signup trial key, enabling agents to access schedules, odds, and player props across NFL, NCAAF, NBA, NCAAB, NHL, and MLB. The API provides measured token budgets for its documentation and supports integration with Cursor, Claude, Copilot, and VS Code.", "body_md": "# AI-assisted development\n\nUse Cursor, Claude, Copilot, or any coding agent to build on Lumify — with MCP tools, machine-readable docs, and copy-paste prompts that prevent hallucinated endpoints.\n\nOverview\n\nLumify is built for agents. You can connect in two ways:\n\n**MCP tools**— the agent calls schedules, odds, splits, and intelligence directly (no wrapper code).** REST + SDKs**— the agent reads llms.txt / OpenAPI and writes correct client code.\n\n| Resource | URL | Measured size | Use when |\n|---|---|---|---|\n| MCP server |\n|\n\n[/docs/cheat-sheet](/docs/cheat-sheet)[/docs/player-props](/docs/player-props)[/docs/forecasts](/docs/forecasts)[/docs/sports-coverage](/docs/sports-coverage)[/SKILL.md](/SKILL.md)*(measured)*[/llms.txt](/llms.txt)*(measured)*[/llms-full.txt](/llms-full.txt)*(measured)*[/docs/llms-full.txt](/docs/llms-full.txt)*(measured)*[/openapi-llms.txt](/openapi-llms.txt)*(measured)*[/docs/openapi](/docs/openapi)·[.md](/docs/openapi.md)[/openapi.json](/openapi.json)*(measured)*[/.well-known/agent.json](/.well-known/agent.json)[/docs/agent-cookbook.md](/docs/agent-cookbook.md)[/changelog](/changelog)·[JSON](/changelog.json)Token budgets are **measured** (UTF-8 bytes ÷ 4), not estimated. Re-measure after regenerating llms-full.txt or OpenAPI.\n\nOne-click install\n\nInstall the hosted MCP server directly, then replace the placeholder API key:\n\nClaude Code (CLI)\n\n```\nclaude mcp add --transport http lumify https://lumify.ai/mcp \\\n  --header \"Authorization: Bearer YOUR_API_KEY\"\n```\n\nCursor (remote HTTP)\n\n```\n{\n  \"mcpServers\": {\n    \"lumify\": {\n      \"url\": \"https://lumify.ai/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer YOUR_API_KEY\" }\n    }\n  }\n}\n```\n\nCursor / Claude Desktop (stdio via npm)\n\nUse the published bridge when the client only speaks local stdio:\n\n```\nnpx -y @lumifyai/mcp\n{\n  \"mcpServers\": {\n    \"lumify\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@lumifyai/mcp\"],\n      \"env\": { \"LUMIFY_API_KEY\": \"YOUR_API_KEY\" }\n    }\n  }\n}\n```\n\nVS Code / Copilot\n\n```\n{\n  \"servers\": {\n    \"lumify\": {\n      \"type\": \"http\",\n      \"url\": \"https://lumify.ai/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer YOUR_API_KEY\" }\n    }\n  }\n}\n```\n\nCLI one-liner: code --add-mcp '{\"name\":\"lumify\",\"type\":\"http\",\"url\":\"https://lumify.ai/mcp\",\"headers\":{\"Authorization\":\"Bearer YOUR_API_KEY\"}}'\n\n**Web connectors:** ChatGPT and Claude.ai browser connectors need OAuth, which Lumify does not implement yet. Use Cursor, Claude Desktop, VS Code, or any Bearer-header MCP client.\n\nGive your agent context\n\nPaste this into CLAUDE.md, .cursorrules, or a project rule file. It is the API's essence compressed for agents (~2.5k tokens of guidance + links to measured artifacts):\n\n```\nYou are integrating with Lumify (also: Lumify AI, lumify.ai) —\nthe agent-ready sports intelligence API at https://lumify.ai.\nNOT affiliated with LUMIFY eye drops, Philips Lumify ultrasound,\nlumifyai.com, or the archived lumifyio/lumify project.\n\n## Read these first (measured token budgets)\n- https://lumify.ai/SKILL.md              (~1.4k tokens) — Agent Skills-format self-onboarding\n- https://lumify.ai/llms.txt              (~5.4k tokens) — overview + pricing + limitations\n- https://lumify.ai/docs/cheat-sheet      — base URL, auth, credits, hero query, errors\n- https://lumify.ai/docs/player-props     — NFL/NCAAF/NBA/NCAAB/NHL/MLB player-prop market catalog\n- https://lumify.ai/llms-full.txt         (~11.7k tokens) — GEO orientation (FAQ, coverage)\n- https://lumify.ai/docs/llms-full.txt    (~81k tokens) — full technical docs + dump\n- https://lumify.ai/openapi-llms.txt      (~6.3k tokens) — endpoint dump alone\n- https://lumify.ai/openapi.json         (~64.7k tokens) — exact schemas\n- https://lumify.ai/docs/agent-cookbook.md — copy-paste recipes\n- https://lumify.ai/changelog.json       — date-stamped changes\n\n## Auth\nAuthorization: Bearer lmfy-...\nInstant trial key (no signup): https://lumify.ai/docs/ai\nNever invent an API key. If you cannot access URLs, ask the user to paste\nthe relevant resource instead of guessing.\n\n## MCP (preferred when available)\nURL: https://lumify.ai/mcp  (Streamable HTTP, JSON mode, stateless)\n23 tools: list_sports, list_seasons, list_events, get_event,\nbatch_get_events, query_events, get_live_score, get_odds,\nget_odds_history, get_stats, get_player_props, get_team_props, get_period_odds, get_splits, get_intelligence, list_ev, list_forecasts,\nlist_teams, get_team, search_players, get_player,\nget_player_events, estimate_cost.\ninitialize / tools/list / ping are free; tools/call metered like REST.\n_meta.credits_used reports the charge. Prefer MCP tools over hand-rolled REST.\n\n## Billing rule (two budgets)\n- Data plane: schedules, scores, odds, splits, stats — typically 1 credit.\n- Intelligence plane: /intelligence — 1 credit when available.\n- One request = 1 credit. include_odds / include_intelligence on GET /v1/events/{id}\n  do not add extra.\n- Errors and available:false responses are NEVER charged.\n- Always estimate first with POST /v1/estimate or MCP estimate_cost (free).\n\n## Boundary litmus\n- /stats and raw odds = deterministic data. No scoring, no tiers.\n- /intelligence = predictive judgment (probability / fair_price / Price overlay / main-line ev).\n\n## Hero endpoints\nGET  /v1/events?sport=mlb&status=scheduled\nGET  /v1/events/{id}?include_odds=true&include_intelligence=true\nGET  /v1/events/{id}/odds?bookmaker=all\nGET  /v1/events/{id}/splits\nGET  /v1/events/{id}/intelligence\nPOST /v1/estimate\nPOST /v1/trial-key   (human Turnstile-gated; prefer /docs/ai button)\n\n## Coverage (keep in sync with llms.txt)\nIntelligence live: MLB, NFL, NCAAF, tennis, soccer (MLS + big-five).\nForecasts: MLB, NFL, NCAAF, NBA, NCAAB, NHL — https://lumify.ai/docs/forecasts\nUCL and other clubs: available: false.\nSplits: MLB, NBA, NHL, NFL.\nBooks: pinnacle (default), fanduel, draftkings, betmgm, caesars,\nbet365, circa, hardrock, betonline.\nPlayer props: NFL/NCAAF/NBA/NCAAB/NHL/MLB on GET /v1/events/{id}/player-props (MCP get_player_props).\nCatalog: https://lumify.ai/docs/player-props\nGET /odds stays moneyline/spread/totals. Futures not on v1.\nAlternate spread/total rungs via include_alts=true. Final /odds includes result.\nOdds cadence ~10 min.\n\n## Model behavior\n- Do not guess or invent endpoints, fields, sport IDs, or credit costs.\n- Help the user choose filters (sport, status, date, has_recommend).\n- When data is unavailable, explain available:false rather than retrying forever.\n- Gate volume, not capability existence — streaming/webhooks are self-serve.\n```\n\nIn Cursor, you can also add https://lumify.ai/llms.txt as a docs/@ reference.\n\nStarter prompts\n\nTry these after MCP is connected (or with the context block above):\n\nLive slate + intelligence\n\n```\nUsing Lumify MCP, list today's MLB games that are scheduled or live.\nFor the top 3 by start time, pull get_intelligence and summarize\nprobability, fair_price, and any main-line ev (Beta).\n```\n\nMain-line EV scan (Beta)\n\n```\nUsing Lumify MCP list_ev, scan MLB for pregame moneyline +EV\nopportunities (min_ev 1). Rank by ev_pct. For the top row, call\nget_intelligence on that event_id and quote fair / ev as Beta\ndisplay packaging of the price gap. Try market=spreads or\nmarket=totals for the same scan on other main lines.\n```\n\nSplits vs public\n\n```\nFind NFL games this week where betting splits show a clear ticket%\nvs handle% divergence. Use list_events then get_splits. Rank by\nthe largest handle/ticket gap and explain what it implies.\n```\n\nLine movement watcher\n\n```\nFor a given event_id, call get_odds and get_odds_history.\nShow opening vs current moneyline/spread/total across supported\nbooks (Pinnacle, FanDuel, DraftKings, BetMGM, Caesars, Bet365,\nCirca, Hard Rock, BetOnline), and flag any reverse line moves.\n```\n\nScaffold a small agent\n\n```\nRead https://lumify.ai/openapi.json and scaffold a TypeScript\nscript that: (1) lists today's MLB events, (2) fetches intelligence\nfor each, (3) prints bets[] probability / fair_price when available\nis true. Do not filter has_recommend — it stays false until Edge.\nUse @lumifyai/sdk if helpful. Do not invent fields.\n```\n\nSDKs\n\nWhen you want typed REST clients instead of (or alongside) MCP:\n\n```\nnpm install @lumifyai/sdk\npip install lumify-sdk\n```\n\nDocs: [@lumifyai/sdk](https://www.npmjs.com/package/@lumifyai/sdk) · [lumify-sdk](https://pypi.org/project/lumify-sdk/) · MCP bridge [@lumifyai/mcp](https://www.npmjs.com/package/@lumifyai/mcp)\n\nNext steps", "url": "https://wpnews.pro/news/show-hn-lumify-sports-intelligence-api-for-agents-try-without-signup", "canonical_source": "https://lumify.ai/docs/ai", "published_at": "2026-08-29 18:12:29+00:00", "updated_at": "2026-08-29 18:48:37.722764+00:00", "lang": "en", "topics": ["ai-tools", "ai-infrastructure", "developer-tools"], "entities": ["Lumify", "Cursor", "Claude", "Copilot", "VS Code"], "alternates": {"html": "https://wpnews.pro/news/show-hn-lumify-sports-intelligence-api-for-agents-try-without-signup", "markdown": "https://wpnews.pro/news/show-hn-lumify-sports-intelligence-api-for-agents-try-without-signup.md", "text": "https://wpnews.pro/news/show-hn-lumify-sports-intelligence-api-for-agents-try-without-signup.txt", "jsonld": "https://wpnews.pro/news/show-hn-lumify-sports-intelligence-api-for-agents-try-without-signup.jsonld"}}