Lumify — Client SDKs & MCP
Official client libraries and Model Context Protocol (MCP) integration for Lumify, the agent-ready sports-intelligence API: real-time schedules, live scores, odds, line movement, public betting splits, and explainable AI bet confidence across MLB, NFL, NCAAF, NCAAB, NBA, NHL, tennis, and soccer (MLS, EPL, La Liga, Serie A, Bundesliga, Ligue 1, and UEFA Champions League).
This repository is the public home for the client SDKs, the MCP stdio bridge, and developer docs/examples. Lumify itself is a hosted API at
https://lumify.ai— you don't run a server yourself.
Get an API key
Everything here authenticates with a Lumify API key (lmfy-...).
- Fastest — no signup: grab a free instant trial key at https://lumify.ai/docs/ai (click "Get instant trial key"). No account, email, or credit card — 100 credits, 14-day expiry. Paste it and start calling.
- Persistent account: create a key at https://lumify.ai/api-keys — free trial with 1,000 credits, no credit card required.
export LUMIFY_API_KEY="lmfy-xxxxxx.yyyyyyyy"
Packages
| Runtime | Package | Install | Docs |
|---|---|---|---|
| TypeScript / JavaScript | @lumifyai/sdk | npm install @lumifyai/sdk | README |
| Python | lumify-sdk | pip install lumify-sdk | README |
| LangChain | langchain-lumify | pip install langchain-lumify | README |
| LlamaIndex | llamaindex-lumify | pip install llamaindex-lumify | README |
| CrewAI | crewai-lumify | pip install crewai-lumify | README |
| MCP stdio bridge | @lumifyai/mcp | npx -y @lumifyai/mcp | README |
Quick start
TypeScript
import { Lumify } from "@lumifyai/sdk";
const client = new Lumify({ apiKey: process.env.LUMIFY_API_KEY! });
const { sports } = await client.sports.list();
const event = await client.events.get(12345, { includeOdds: true, includeIntelligence: true });
console.log(event.status, event.intelligence?.bets);
Python
import os
from lumify import Lumify
client = Lumify(api_key=os.environ["LUMIFY_API_KEY"])
sports = client.sports.list()
event = client.events.get(12345, include_odds=True, include_intelligence=True)
print(event["status"], event.get("intelligence"))
curl
curl https://lumify.ai/v1/events?sport=nfl&status=inprogress \
-H "Authorization: Bearer $LUMIFY_API_KEY"
Use it from an AI agent (MCP)
Lumify runs a hosted MCP server at https://lumify.ai/mcp (Streamable HTTP,
JSON mode, stateless). Point any MCP-compatible client at it.
Remote (Cursor, VS Code, Claude Desktop with remote support):
{
"mcpServers": {
"lumify": {
"url": "https://lumify.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
Local stdio (clients without remote MCP support):
{
"mcpServers": {
"lumify": {
"command": "npx",
"args": ["-y", "@lumifyai/mcp"],
"env": { "LUMIFY_API_KEY": "YOUR_API_KEY" }
}
}
}
See the MCP bridge README and the MCP guide for the full tool catalog.
Examples
| Demo | Path | Tutorial |
|---|---|---|
| Live sports scoreboard | examples/scoreboard | Build a live sports scoreboard |
cd examples/scoreboard
npm install && cp .env.example .env # set LUMIFY_API_KEY
npm start # → http://localhost:3000
Documentation
- API reference: https://lumify.ai/docs/reference
- OpenAPI: https://lumify.ai/docs/openapi (schema:
/openapi.json· ReDoc · Swagger UI) - Guides (incl. MCP): https://lumify.ai/docs/guides
- Quick start:
docs/getting-started/quick-start.md - Agent cookbook:
docs/agent-cookbook.md - Postman collection:
docs/lumify.postman_collection.json
Support & contributing
- Questions and bugs: open an issue
- Contribution guidelines:
CONTRIBUTING.md
License
MIT © 2026 Lumify AI