Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Lumify Sports Intelligence API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Flumify.ai%2Flumify" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Flumify.ai%2Flumify" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Lumify Sports Intelligence API.
List events by sport, league, status, and date, and fetch one event with odds and intelligence included
Read current odds by bookmaker and line movement history for an event
Pull public bets% and handle% splits per side with a cross-book consensus for US leagues
Get player-prop, team-total, and period lines with live progress for an event
GET STARTED
Score a game's bets with confidence scores, signal breakdowns, and narratives, and list main-line EV opportunities
Grade player-prop and game-market legs on a bet slip as over, under, push, in_progress, or dnp
Resolve a messy player or team name to a Lumify id before querying
Patterns agents use Lumify Sports Intelligence API for, with concrete tasks.
★ AI betting assistant answering game questions
A sports assistant agent asked 'what is the line on tonight's Lakers game' needs to find the event, read odds, and add context. Through Jentic the agent searches for 'get odds for a game', resolves the team with POST /v1/resolve/team, lists events with GET /v1/events, and reads GET /v1/events/{event_id}/odds and GET /v1/events/{event_id}/splits. The bearer key is injected by Jentic at call time, and the agent answers with bookmaker-specific numbers.
POST /v1/resolve/team with query 'Lakers', call GET /v1/events with sport 'nba', the resolved team_id, and today's date, then fetch GET /v1/events/{event_id}/odds with bookmaker 'draftkings' and summarise the spread and total
Bet slip grading
Apps that track user bets need to settle each leg once games finish. POST /v1/grade/slip grades player-prop legs on NFL, NBA, NCAAF, NCAAB, NHL, MLB, and soccer, plus h2h, spreads, and totals game markets, returning over, under, push, in_progress, dnp, or no_stat. Structured legs with event_id and player_id grade most reliably; free-text legs are graded only when the player and event resolve uniquely.
POST /v1/grade/slip with legs containing an event_id, a player_id, the market, and the line for each prop, then report which legs hit
EV screening and forecast research
Bettors looking for value can list main-line EV opportunities with GET /v1/intelligence/ev, filtered by sport, league, market, min_ev, and book, and list forecasted player-prop wagers with GET /v1/intelligence/forecasts by sport and date. GET /v1/events/{event_id}/intelligence adds confidence scores and signal breakdowns for a single game.
Call GET /v1/intelligence/ev with sport 'nhl' and min_ev 3, then fetch GET /v1/events/{event_id}/intelligence for the top three results
Live scoreboard and alerts
Scoreboards and alerting bots need score changes as they happen. GET /v1/events/{event_id}/score returns the current score, GET /v1/events/{event_id}/stream streams live score updates over server-sent events, and webhook subscriptions under /v1/webhooks push updates to your endpoint with a delivery history per subscription.
Create a webhook subscription with POST /v1/webhooks for live score updates, then check GET /v1/webhooks/{subscription_id}/deliveries for failed deliveries
191 endpoints — the lumify sports intelligence api serves schedules, live scores, betting odds, line movement, public betting splits, and bet intelligence across mlb, tennis, soccer including the epl and uefa champions league, nfl, ncaaf, ncaab, nba, and nhl.
METHOD
PATH
DESCRIPTION
/v1/events
List events
/v1/events/{event_id}/odds
Current odds for an event
/v1/events/{event_id}/odds/history
Line movement history
/v1/events/{event_id}/splits
Public betting splits
/v1/events/{event_id}/intelligence
Bet intelligence for an event
/v1/intelligence/ev
Main-line EV opportunities
/v1/grade/slip
Grade bet slip legs
/v1/resolve/player
Resolve a player name to an id
/v1/events
List events
/v1/events/{event_id}/odds
Current odds for an event
/v1/events/{event_id}/odds/history
Line movement history
/v1/events/{event_id}/splits
Public betting splits
/v1/events/{event_id}/intelligence
Bet intelligence for an event
/v1/intelligence/ev
Main-line EV opportunities
/v1/grade/slip
Grade bet slip legs
/v1/resolve/player
Resolve a player name to an id
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Lumify by hand means sorting its /v1 data routes, which take an lmfy- bearer key, from dashboard, billing, and webhook routes that use other schemes, then handling 402 credit blocks and X-Credits headers yourself. Through Jentic you install once, import Lumify from the API Directory, store the key once, and your agent calls it.
Permission scoping
Lumify puts the event id in the URL path (/v1/events/{event_id}/odds, /v1/events/{event_id}/splits), so a rule can pin your agent to one event's operations. You choose the operations it may call, so spending or account operations like POST /api/agent/credits/topup or DELETE /api/agent/keys/{key_id} are not included unless you add them.
Credential isolation
Your Lumify API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get betting splits for a game' or 'grade a bet slip', and Jentic returns the matching Lumify operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Lumify Sports Intelligence API through Jentic.
What authentication does the Lumify Sports Intelligence API use?
The data routes under /v1 use ApiKeyBearer, an HTTP bearer key in the form Authorization: Bearer lmfy-..., and the /api/agent key and credit routes use the same scheme. The spec also declares SessionCookie (the lumify_session dashboard cookie) for account, billing, and admin pages, StripeSignature (the Stripe-Signature header) for the Stripe webhook receiver, and GcpAlertToken (a token query parameter) for a monitoring webhook. GET /v1/health and the public docs pages are open.
Which sports does the Lumify Sports Intelligence API cover?
Per the spec, coverage spans MLB, tennis, soccer (MLS, EPL, La Liga, Serie A, Bundesliga, Ligue 1, and UEFA Champions League), NFL, NCAAF, NCAAB, NBA, and NHL. Public betting splits are available for MLB, NBA, NHL, NFL, NCAAF, and NCAAB but not tennis or soccer.
What are the rate limits for the Lumify Sports Intelligence API?
The OpenAPI spec does not list numeric limits, but it states that responses include X-RateLimit and X-Credits headers, and that billing blocks return 402 with codes such as insufficient_credits or daily_credit_cap_exceeded rather than 401. See https://lumify.ai/docs/rate-limits for the current limits, and use POST /v1/estimate to price a planned call.
Is there a Lumify MCP server?
You don't need an MCP server to give your agent Lumify. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the event, odds, and grading operations it needs, discovered on demand rather than preloaded as tool definitions into its context.
Can I limit what my agent is allowed to do with Lumify?
Yes. For example, write a rule that allows only GET /v1/events, GET /v1/events/{event_id}/odds, and GET /v1/events/{event_id}/splits, so the agent can look up games and read lines but cannot create webhooks, mint keys through POST /api/agent/keys, or buy credits through POST /api/agent/credits/topup. Every call it makes is logged.
How do I get odds for a game through Jentic?
Add Lumify to your Jentic One instance from the directory and store your lmfy- key. Your agent searches for 'get odds for a game', loads the matching operation, and calls GET /v1/events/{event_id}/odds with an optional bookmaker such as draftkings or fanduel. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I try Lumify without signing up?
POST /v1/trial-key issues a throwaway key with no signup, 100 lifetime credits, and a 14-day expiry, limited to one per network per 7 days and gated by a Cloudflare Turnstile token. The spec says it is meant for the docs page trial button, not a persistent integration, so register an account for ongoing use.
For Agents
Read sports schedules, live scores, odds, line movement, betting splits, player props, injuries, and AI bet intelligence across major leagues, and grade bet slips.
Use for: Get tonight's NBA games with current odds, Show me the line movement for this NFL game, Check whether the public is on the favourite in this MLB game, Find positive EV bets in the NHL today
Not supported: Does not place bets, hold wagering balances, or run fantasy contests. Use for reading sports schedules, scores, odds, splits, props, injuries, and bet intelligence and for grading slips only.
The Lumify Sports Intelligence API serves schedules, live scores, betting odds, line movement, public betting splits, and bet intelligence across MLB, tennis, soccer including the EPL and UEFA Champions League, NFL, NCAAF, NCAAB, NBA, and NHL. Each event exposes current odds by bookmaker, odds history, player-prop and team-total lines with live progress, period odds such as first-half lines, injuries, and raw match statistics. Intelligence routes add confidence scores, signal breakdowns, and generated narratives per event, list main-line EV opportunities and forecasted player-prop wagers, and grade bet-slip legs as over, under, push, or dnp. Resolver endpoints map messy player, team, and event strings to Lumify ids, and live scores can be streamed over SSE or pushed by webhook.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>