chess.ceo

Fuzzy name lookup for FIDE-rated chess players.

Full stats for one player: identity, monthly rating history, peak / trend stats, career W/D/L by color and time control, top-10 openings as White and Black, opponent analysis by rating bracket, notable wins and worst losses, top events with performance ratings.

Create a prep SESSION combining games from one or more sources — FIDE database, Chess.com account, Lichess account — with optional filters (colour, date range, time control).

Query one position within a prep session created by `prepare_opponent`.

List the caller's active prep sessions with their tokens and metadata.

Delete one prep session by token.

Move statistics + example games at a position.

**CALL WHEN**: about to write ANY comment on a position that describes what's happening on the board — piece activity, structure, plans, weaknesses.

Neural net (ResNet-20x256) trained on real games.

Complete head-to-head record between two players.

Tournaments currently being broadcast live on chess.ceo.

Players participating in one live-broadcast tournament.

Which currently-live broadcasts a given player is competing in.

Returns the catalog of combo cloud-engine machine types the user can start (SKU, human display name, cost per hour, availability).

Rent a combo GPU instance (Stockfish + Lc0 in the same container) on the user's chess.ceo account.

List the user's currently running cloud engines.

Destroy a running cloud engine.

Runs a synchronous ~2s analysis on the user's running combo instance and returns both Stockfish and Lc0's final read for the FEN — depth, top-N candidate moves with scores (**scoreCp is White-POV centipawns**: +20 = White is +0.20 pawns better regardless of whose turn it is; matches the sign convention used everywhere else in this MCP, including the stored ceoEval).

List the user's own PGN collections — every collection they've created, not just prep files.

List the games (prep files) inside one of the user's collections.

Text search over the user's prep files ACROSS ALL their collections (matches PGN headers, comments, and content).

Position search across every one of the user's EDITABLE prep files (all their non-encrypted collections).

Read one prep file.

Cheap tree queries without reading the whole file.

Group every position in a prep file that appears more than once — the same piece placement + side-to-move + castling rights reached by different move orders.

Create a new (empty) prep file in the specified collection.

Soft-delete a prep file.

Restore a previously soft-deleted prep file.

Append a move as a new child of the node identified by `parent_id`.

Append a linear sequence of moves under `parent_id`.

Set (or clear, with empty string) the text comment on the node identified by `node_id`.

Replace the list of NAGs on the node identified by `node_id`.

Replace the visual annotations (arrows + coloured squares) on the node identified by `node_id`.

Delete the node identified by `node_id` and all its descendants.

Make the node identified by `node_id` its parent's mainline (children[0]), demoting the current mainline (and any other siblings) into variation order.

Batch: apply a list of mutations in one call.

Walk the tree from `node_id` (default `'r'` = whole file) and populate the persistent `ceoEval` on every descendant via cloud_analyse.

Poll the status of an auto_evaluate job.

Ask a running auto_evaluate job to stop as soon as its current node finishes.

Start a long Stockfish think on a single position (up to 5 min movetime).

Poll a deep_analyse job.

Ask a running deep_analyse job to stop early.

Look up which of the USER's own Chessable / PGN courses cover a position.

Read the actual commentary + variations from a course file at a specific position.

Return the stored engine eval for a node, or null if that node was never analysed.

Set or clear a game-level PGN tag (Event, Site, Date, White, Black, Result, or any custom tag).

Returns the full chess.ceo engine-usage guide: when to trust Stockfish (objective truth) vs Lc0 (practical eval), how to read disagreements between them, and how to use Lc0 contempt to find non-objective 'practical' ideas.

**CALL WHEN**: the user asks about OPENING PREPARATION — 'prep me against X', 'what should I play vs the Najdorf', 'help me build a repertoire against 1.e4', 'walk this opponent's Sveshnikov'.

**CALL WHEN**: you're about to CREATE, LIST, SAVE, or DELETE a prep file — the persistent file storage feature.

Returns the guide on how to write correct, useful PGN — mainline discipline, variations as moves (never prose describing moves), NAG symbols including novelty ($146), unclear ($13), compensation ($44) and the standard set, ChessBase arrow/coloured-square syntax ([%cal] / [%csl]), and common pitfalls the parser will reject.

**CALL WHEN**: about to write ANY prose commentary in a prep file, ever.

One call, three parallel fetches at the same position: opponent's stats on their side, your stats on your side, and the 11.7M-game general database at that position.