A fully offline cricket stats engine that bundles 1,317 matches and 312,309 deliveries from IPL 2026, 18 seasons of IPL history, and Major League Cricket. No API keys, no network calls. The 32 tools cover player profiles, head-to-head matchups, venue patterns, dismissal breakdowns, live scorecards, and historical leaderboards. Every response includes a canonical URL back to players.cricketstudio.ai, a data freshness timestamp, and sample size metadata. Batting claims require 30 balls faced minimum, bowling claims need 15 deliveries. Reach for this when you need citable cricket stats with provenance baked in, or when you're building cricket analysis features without rate limits or API dependencies.
CRICKETSTUDIO_DEV_IDOptional developer ID for usage tracking and early hosted-API access. Register free at players.cricketstudio.ai/developers.
CRICKETSTUDIO_NO_TELEMETRYSet to '1' to disable anonymous startup telemetry.
Citation infrastructure for cricket — 32 MCP tools (incl. a knowledge-graph layer), zero network calls, 1,317 matches, 312,309 deliveries.
CricketStudio MCP is a Model Context Protocol server that gives any MCP-compatible AI client — Claude Desktop, Cursor, ChatGPT Connectors, and others — structured, citable access to cricket data. Every response carries a canonicalUrl back to players.cricketstudio.ai, an explicit date window, a sample-size count, and a provenance trail to the underlying ball-by-ball corpus. The data is fully bundled in data/snapshot/ — tool answers are computed locally with no data-fetch calls, no API keys, and no rate limits. (The package sends one anonymous startup ping for usage counts; disable it with CRICKETSTUDIO_NO_TELEMETRY=1.)
The corpus covers IPL 2026 (complete season, RCB champions), 18 seasons of IPL history (2007/08–2025, Cricsheet), and Major League Cricket 2023–2026 (Cricsheet). Batting claims require a minimum of 30 balls faced; bowling claims require 15 deliveries. Claims that do not clear those floors are not surfaced.
Add to your Claude Desktop config file and restart the app.
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"cricketstudio": {
"command": "npx",
"args": ["cricketstudio-mcp"]
}
}
}
npx cricketstudio-mcp
Any MCP client that supports the stdio transport can use this command directly. The server starts on stdin/stdout and requires Node 20 or later.
All 32 tools work fully against the bundled snapshot. Each response includes canonicalUrl, dataAsOf, and sampleSize.
| Tool | What it returns | Maps to URL |
|---|---|---|
get_dataset_summary | Top-level corpus overview: seasons, matches, players, deliveries | / |
search_players | Player discovery by name or team | n/a |
get_player_profile | Headline stats across all five pillars (P1–P5) | /players/{slug} |
get_player_pillar | Claims from a specific pillar (P1 recaps, P2 moments, P3 form, P4 season, P5 notebook) | /players/{slug} filtered |
list_atomic_claims | Filtered query across all ClaimReview entries | various |
compare_players | Side-by-side stat comparison for two or more players | /compare/players?slugs=… |
get_team_profile | Team headline stats and season summary | /teams/{slug} |
get_team_h2h | Head-to-head record between two franchises | /teams/{a}/vs/{b} |
get_venue_hub | Aggregated venue patterns: par scores, toss impact, phase splits | /venues/{slug} |
get_standings | IPL 2026 points table with NRR | /standings |
get_trend | A single trend insight with full claim set | /trends/{id} |
list_trends | Browse trends by category (conditional, momentum, venue, toss, anomaly) | /trends |
get_player_h2h | Batter vs bowler matchup record | /h2h/{batter}-vs-{bowler} |
get_season_stats | Season leaderboard for a given aspect (runs, wickets, strike rate, economy, …) | /season/ipl-2026/{aspect} |
get_fielding_stats | Catches, run-outs, and fielding contributions for a player or the full season | /players/{slug} · /season/ipl-2026/catches |
get_partnerships | Partnership records for a match or player pair | /matches/{id} |
get_dismissal_analysis | Dismissal mode breakdown for a batter or bowler | /players/{slug} |
list_fixtures | Full schedule with match status, venue, and result | /matches |
get_match_state | Live or final scorecard with ball-by-ball state | /matches/{fixture-id} |
get_match_recap | Atomic claim set for a completed match | /matches/{fixture-id} |
| Tool | What it returns | Maps to URL |
|---|---|---|
get_mlc_dataset_summary | MLC corpus overview: seasons, matches, players, deliveries | /leagues/mlc |
search_mlc_players | Player discovery within the MLC corpus | /leagues/mlc/players |
get_mlc_player_profile | MLC career and season stats for a player | /leagues/mlc/players/{slug} |
get_mlc_team_profile | Franchise profile and season history | /leagues/mlc/teams/{slug} |
get_mlc_match | Match scorecard and key claims | /leagues/mlc/matches/{id} |
get_mlc_match_claim | A single typed claim for an MLC match (top scorer, best figures, etc.) | /leagues/mlc/matches/{id}/c/{kind} |
list_mlc_matches | All MLC matches with status and results | /leagues/mlc/matches |
list_mlc_leaderboards | Season or all-time leaderboard for a given MLC aspect | /leagues/mlc/leaderboards/{aspect} |
| Tool | What it returns | Maps to URL |
|---|---|---|
get_ipl_leaderboard | All-time IPL leaderboard for any aspect across 18 seasons (2007/08–2025) — runs, wickets, sixes, centuries, economy, and more | /leagues/ipl/leaderboards/{aspect} |
Slug-keyed traversal over CricketStudio's entity graph. Nodes are players and franchises; edges are plays_for (squad membership) and faced/dismissed_by (batter-vs-bowler matchups, mirroring the get_player_h2h pair set).
| Tool | What it returns | Maps to URL |
|---|---|---|
get_related_entities | Entities connected to a player or franchise, by edge type and direction | /players/{slug} · /teams/{slug} |
get_player_connections | A player's franchise + most-faced bowlers + bowlers who dismissed them most, in one call | /players/{slug} |
get_graph_path | Shortest connection (≤4 hops) between two entities, e.g. two players via a shared franchise | n/a |
Once connected in Claude Desktop, you can ask questions like:
| Source | Coverage | License |
|---|---|---|
| Licensed feed | IPL 2026 ball-by-ball (complete season — RCB champions) | Proprietary |
| Cricsheet | IPL historical, 18 seasons, 1,169 matches (2007/08–2025) | CC BY 3.0 |
| Cricsheet | MLC 2023–2026, 138 matches | CC BY 3.0 |
Total corpus: 1,317 matches · 312,309 ball-by-ball deliveries.
Sample-size floors (publicly disclosed):
Claims that do not reach these floors are excluded — they are not suppressed with a placeholder, they are simply absent. This is the moat.
Update cadence: the bundled snapshot is refreshed after each CricketStudio data update. Every tool response includes dataAsOf so an LLM citing the answer can disclose freshness explicitly.
Data licence: the bundled data is released under CC BY 4.0. Every tool response includes a canonicalUrl back to players.cricketstudio.ai so attribution flows automatically when an LLM cites an answer.
This package bundles a pre-computed projection of CricketStudio's public data. Every number here is also readable on the rendered pages at players.cricketstudio.ai — no new information is exposed, only a different (offline, zero-network) access path.
Every claim in this package is governed by five non-negotiables:
ipl-2026, ipl-career, last-N-matches). No "all-time" labels without a defined window.[Subject] [metric] [value] [comparator] [period].Full methodology at https://players.cricketstudio.ai/about.
npm install
npm run typecheck # tsc --noEmit
npm start # stdio MCP server via tsx
Smoke-test without an MCP client — spawns the server over stdio, drives it with JSON-RPC, and asserts every advertised tool returns a non-error payload with dataAsOf:
npm run smoke
Register at cricketstudio.ai/developers to get early access to the hosted HTTP transport (mcp.cricketstudio.ai), live ball-by-ball endpoints, API-key tiers, and the full 29-tool catalog with live data rather than snapshots.
LICENSEhttps://players.cricketstudio.ai). Attribution flows automatically via the canonicalUrl field in every tool response.Built by Arul Anand · Chennai & Frisco · cricket enthusiast and data engineer. Questions, bugs, or requests: open an issue or visit players.cricketstudio.ai/mcp.