kingsplaybook-mcp
LocalAbout kingsplaybook-mcp
kingsplaybook-mcp connects AI agents and sports analytics tools to KingsPlaybook's API for NBA, MLB, and NHL data. It provides a local stdio wrapper for lineups, projections, game lines, pick history, and data freshness.
Key features
- 01Retrieve confirmed NBA, MLB, and NHL lineups
- 02Fetch player projections
- 03Access aggregated game lines
- 04Review posted pick history and results
- 05Check data freshness by domain
Use cases
- 01Inspect confirmed lineups for a league and date
- 02Retrieve player projections for a slate
- 03Review past picks alongside results and closing lines
MCP support
The local stdio MCP server exposes KingsPlaybook API data as tools. MCP clients run it with an API key to retrieve lineups, projections, game lines, pick history, and freshness signals.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y kingsplaybook-mcpKINGSPLAYBOOK_API_KEYSecretYour kp_live_ API key from https://kingsplaybook.org/devsKINGSPLAYBOOK_API_URLOverride the API base URL (default https://api.kingsplaybook.org)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
5Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| date | string | Yes | Game date, ISO-8601 (YYYY-MM-DD) |
| league | enum | Yes | League: nba, mlb, or nhlnba | mlb | nhl |
Details
From the project READMEkingsplaybook-mcp
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.
Get an API key
Sign up at kingsplaybook.org/devs. The
Free tier covers lineups; paid tiers add projections, lines, and history.
Your key looks like kp_live_….
Install
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.
Tools
| Tool | What it returns | Min. plan |
|---|---|---|
kingsplaybook_get_lineups | Confirmed lineups for a league + date | Free |
kingsplaybook_get_projections | Raw player projections for a league + date | Starter |
kingsplaybook_get_lines | Canonical game lines for a league + date | Pro |
kingsplaybook_get_pick_history | Posted picks + results for a date | Premium |
kingsplaybook_get_freshness | 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.
Examples
- "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" })
Configuration
| Env var | Required | Default | Purpose |
|---|---|---|---|
KINGSPLAYBOOK_API_KEY | yes | — | Your kp_live_ API key |
KINGSPLAYBOOK_API_URL | no | https://api.kingsplaybook.org | Override the API base URL |
Local development
npm install
npm run build # compile TypeScript to dist/
npm start # run the built server (needs KINGSPLAYBOOK_API_KEY)
npm run dev # watch mode
Links
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.