sportiq-mcp

MCP server that turns any AI assistant into a sports analyst across FIFA World Cup 2026 football, Formula 1, and IPL cricket — 44 AI-callable tools.

SportIQ running live in Claude — Monte Carlo World Cup bracket, F1 pit strategy, and Dream11 optimisation, each a visible MCP tool call. (1-min demo)

Every tool is free — the three flagships and everything in the INTEL columns below, no key, no account. If SportIQ is useful to you, sponsor the project to support ongoing development. It's a donation, not a paywall — nothing is locked behind it.

What it does

Raw-data tools are table stakes; the intelligence layer is the product. Three flagships:

• football_simulate_bracket — Monte Carlo with Poisson xG over the 48-team WC 2026 format → per-team round + title probabilities.

• f1_predict_pit_strategy — tyre-degradation model on OpenF1 telemetry → optimal stop laps + compound sequence.

• cricket_build_dream11_team — PuLP constraint solver → a valid fantasy XI under credit/role/team caps.

Tools (44 total)

Plus sportiq_health (cache backend + per-adapter status and remaining API quota).

Data sources (per chain, with keyless fallbacks): football → API-Football → football-data.org → bundled wc2026.json. F1 → OpenF1 → Jolpica → fastf1. Cricket → CricAPI + static seeds (NDTV/Cricbuzz scrapers opt-in).

Related MCP server: wc26-mcp

Where it works

Anywhere that speaks MCP — Claude (Desktop + web), ChatGPT, Cursor, and any MCP client. Two ways to run it:

• Hosted (no install): add a custom connector — works in claude.ai web & ChatGPT.

• Local (uvx/Desktop config/IDEs): install from PyPI.

How it works

Hosted — no install

A public instance runs on Google Cloud Run. Add this as a custom connector with No authentication:

https://sportiq-mcp-329580761892.us-central1.run.app/mcp

• claude.ai (web): Settings → Connectors → Add custom connector → paste URL → Save.

• ChatGPT: Settings → Apps & Connectors → enable Developer mode → Create app (MCP) → paste URL → No authentication → Connect.

All 44 tools work out of the box on the plain URL above — data tools and the full intelligence layer (bracket simulation, pit strategy, Dream11, value bets). No key, no account, nothing to unlock.

First request after idle takes ~5–10s (the server scales to zero, so it wakes up); fast after that.

Local install

uvx sportiq-mcp                       # from PyPI
# or from source:
git clone https://github.com/Ninjabeam20/SportIQ-MCP && cd sportiq-mcp
uv sync && uv run python -m sportiq.server

Claude Desktop config:

{
  "mcpServers": {
    "sportiq": {
      "command": "uvx",
      "args": ["sportiq-mcp"],
      "env": {
        "CRICAPI_KEY": "your_cricapi_key",
        "APIFOOTBALL_KEY": "your_apifootball_key",
        "THEODDS_KEY": "your_theodds_key"
      }
    }
  }
}

Every tool works with no keys — the server boots and serves seed/free-source data, and the whole intelligence layer runs locally. Data-source keys are optional and only upgrade the source a tool reads from (fresher/live data); they never unlock tools.

macOS arm64: the Dream11 solver needs CBC — brew install cbc (the binary bundled with PuLP is x86-only).

Self-host

Set SPORTIQ_TRANSPORT=http and the server serves the MCP endpoint at /mcp (binds 0.0.0.0:$PORT). A ready-to-build Dockerfile is included; see cloud.md for a Google Cloud Run deploy (free tier). With your own keys set, the live-score and odds tools come online too.

Support SportIQ

Every tool is free and open source — the raw-data tools, sportiq_health, and the full intelligence layer (the three flagships + everything in the INTEL columns). No key, no account, nothing gated.

If SportIQ saves you time, sponsor the project at github.com/sponsors/Ninjabeam20 to help fund hosting and ongoing development. It's a voluntary donation — you get the same fully-unlocked server either way.

Is it safe?

• Open source, MIT licensed, published on PyPI with signed build attestations — read the code before you connect it.

• Read-only. Tools only fetch and analyse public sports data — no write, delete, payment, email, or file-system tools.

• No data collection. It answers a tool call and forgets it.

• The hosted instance holds no secrets — it runs with zero API keys.

• Independently reviewed by AI code-audit agents (verdict: ship-ready, clean) — see SECURITY.md for the full trust model.

Every response carries a meta.is_stale flag + data age, so the AI tells you how fresh each answer is. Live scores refresh ~30s, F1 telemetry ~10s, standings ~10min, fixtures ~6h.

Develop

uv sync --extra dev
uv run pytest
uv run ruff check .
npx @modelcontextprotocol/inspector uv run python -m sportiq.server

See CLAUDE.md for collaboration rules and docs/index.md for the wiki entry point.

Data sources & credits

SportIQ derives some model constants offline from open datasets. Raw datasets are never shipped or fetched at runtime — only small derived seeds (circuits.json, venues.json, elo_seed.json) are committed.

• F1DB (CC BY 4.0) — per-circuit stop counts + lap lengths; pit loss measured offline from OpenF1 laps.

• Cricsheet — ball-by-ball IPL data → derived venue scoring priors (venues.json).

• martj42 international football results (CC0) — Elo backtesting.

• OpenF1 — keyless live F1 telemetry (runtime source).

• football-data.org — free football data (runtime source).

License & author

Created and maintained by Utkarsh Gupta (@Ninjabeam20). Licensed under the MIT License — © 2026 Utkarsh Gupta. Canonical package: sportiq-mcp on PyPI / io.github.Ninjabeam20/sportiq-mcp in the official MCP registry.