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., "@kingsplaybook-mcp Show me tonight's NBA confirmed lineups"
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.
The official MCP server for the KingsPlaybook Developer API. It gives an AI agent — one building a sports-betting bot, a model, or an analytics tool — direct access to KingsPlaybook's data as native tools:
Confirmed lineups — NBA, MLB, NHL
Player projections — the projection engine's raw output
Canonical game lines — moneyline / spread / total, aggregated across books
Pick-history archive — the publicly-posted record, with results + closing lines
It's a thin local (stdio) wrapper over the /v1 REST API.
Same data, second protocol.
Sign up at kingsplaybook.org/devs. The
Free tier covers lineups; paid tiers add projections, lines, and history.
Your key looks like kp_live_….
Related MCP server: AltSportsData MCP Server
No install step — run it straight from npm with npx. Add it to your MCP
client config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"kingsplaybook": {
"command": "npx",
"args": ["-y", "kingsplaybook-mcp"],
"env": {
"KINGSPLAYBOOK_API_KEY": "kp_live_your_key_here"
}
}
}
}That's it — the agent now has the KingsPlaybook tools.
Tool | What it returns | Min. plan |
| Confirmed lineups for a league + date | Free |
| Raw player projections for a league + date | Starter |
| Canonical game lines for a league + date | Pro |
| Posted picks + results for a date | Premium |
| Per-domain data-age signal | Free |
Every tool returns JSON. Calling a tool above your plan tier returns a
clear 403 message with an upgrade link.
"What's tonight's NBA slate look like?" → kingsplaybook_get_lineups({ league: "nba", date: "2026-05-21" })
"Pull MLB projections for today" → kingsplaybook_get_projections({ league: "mlb", date: "2026-05-21" })
"How did KingsPlaybook's prop picks do yesterday?" → kingsplaybook_get_pick_history({ date: "2026-05-20", type: "prop" })
Env var | Required | Default | Purpose |
| yes | — | Your |
| no |
| Override the API base URL |
npm install
npm run build # compile TypeScript to dist/
npm start # run the built server (needs KINGSPLAYBOOK_API_KEY)
npm run dev # watch modeMIT
Per-domain data-age signal — when the projection pipeline, lineups, and lines were each last updated. Check this to decide whether the data is fresh enough before acting on it. Works on any plan.
Args: none. Returns JSON: { data: { snapshot: { latest_farmer_harvest_at, latest_crown_scored_at }, lineups: { latest_updated_at }, lines: { latest_updated_at } }, meta: { as_of } }.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
KingsPlaybook's canonical game-market lines — moneyline, spread, and total — aggregated across tracked sportsbooks, per game on a league + date. Requires a Pro plan or higher.
Args: league ('nba' | 'mlb' | 'nhl'), date ('YYYY-MM-DD'). Returns JSON: { data: [ { event_id, home_team, away_team, markets: [ { market_type, selections: [ { selection, line, prices: [ { book, price, decimal } ] } ] } ] } ], meta }.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Game date, ISO-8601 (YYYY-MM-DD) | |
| league | Yes | League: nba, mlb, or nhl |
Confirmed / projected starting lineups for every game on a given league + date, split into home and away rosters. Available on every KingsPlaybook plan, including Free.
Args: league ('nba' | 'mlb' | 'nhl'), date ('YYYY-MM-DD'). Returns JSON: { data: [ { event_id, league, game_date, home_team, away_team, lineups: { home: [players], away: [players] }, updated_at } ], meta: { count, league, date, as_of } }.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Game date, ISO-8601 (YYYY-MM-DD) | |
| league | Yes | League: nba, mlb, or nhl |
KingsPlaybook's publicly-posted picks for a date — game-market and player-prop — each with its result and closing-line context. Use this to backtest against the actual posted record. Requires a Premium plan.
Args: date ('YYYY-MM-DD'); optional type ('game' | 'prop', omit for both); optional sport (e.g. 'nba'). Returns JSON: { data: { game_picks: [...], prop_picks: [...] }, meta: { count, game_pick_count, prop_pick_count, date, ... } }.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Game date, ISO-8601 (YYYY-MM-DD) | |
| type | No | Filter to game-market or player-prop picks; omit for both | |
| sport | No | Optional sport filter, e.g. nba, mlb, nhl |
Raw player stat projections — KingsPlaybook's model output, the projected number only — for every game on a league + date. Requires a Starter plan or higher.
Args: league ('nba' | 'mlb' | 'nhl'), date ('YYYY-MM-DD'). Returns JSON: { data: [ { player_name, stat_type, line, direction, projection, league, event_id, game_date, updated_at } ], meta: { count, league, date, tier, as_of } }.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Game date, ISO-8601 (YYYY-MM-DD) | |
| league | Yes | League: nba, mlb, or nhl |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0kingsplaybook_get_freshnesskingsplaybook_get_lineskingsplaybook_get_lineupskingsplaybook_get_pick_historykingsplaybook_get_projectionsScored across 5 tools
Each tool targets a distinct data type: lineups, projections, lines, pick history, and freshness. The boundaries are clear and descriptions explicitly differentiate the content, so there is no ambiguity between tools.
All tools follow the exact pattern 'kingsplaybook_get_<resource>' using snake_case. The resource names are descriptive and consistent (lineups, projections, lines, pick_history, freshness), with no mixed conventions or vague verbs.
Five tools is well-scoped for a specialized sports data API. Each tool represents a core data category necessary for the server's purpose, with no redundancy or unnecessary additions.
The tool set covers all major data retrieval needs for a betting-focused sports data service: lineups, projections, lines, pick history, and freshness verification. For a read-only analytical domain, this is comprehensive and leaves no critical dead ends.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.