io.github.hft-studio/pokerdata

Est-ce que io.github.hft-studio/pokerdata est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.hft-studio/pokerdata » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 32 outils

• compare_strategies≈ 1714 tokens

  Preferred tool for differences between two preflop or postflop contexts. The server fetches both strategies and returns action-frequency/EV deltas plus the largest postflop combo changes, avoiding two large node payloads.

  Paramètres, retour & exemple (7)

  Paramètres

  • anteBb · number · optionnel
    Requested ante in bb. nlmtt8 models a 1bb BB-ante; other positive antes return unsupported coverage.
  • domain · string · requis · preflop | postflop
    Preflop contexts use game/stack/history/hand. Postflop contexts use pack/board/path/combo.
  • format · string · optionnel · cash | mtt
    Requested poker format. "cash" uses the cash trees. "mtt" is supported only for preflop chip-EV against game nlmtt8; ICM, PKO, and satellite remain unsupported.
  • baseline · object · requis
    The context deltas are measured from. One side of the comparison. Preflop contexts use game, stack, history and optional hand; postflop contexts use pack, board, path and optional combo.
  • objective · string · optionnel · solver_ev | chip_ev | icm | pko | satellite
    Requested optimization objective. chip_ev is supported for nlmtt8 preflop. ICM, PKO, and satellite return unsupported coverage.
  • comboLimit · number · optionnel
    Maximum largest-changing combos for aggregate postflop comparisons (default 12, maximum 50)
  • comparison · object · requis
    The context deltas are measured to. One side of the comparison. Preflop contexts use game, stack, history and optional hand; postflop contexts use pack, board, path and optional combo.

  Exemple d'appel

  {"name": "compare_strategies", "arguments": {"domain": "preflop", "baseline": {}, "comparison": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "context": {}, "coverage": {}, "warnings": [], "schemaVersion": "texte"}}

• enqueue_solve≈ 722 tokens

  Record a heads-up postflop solve request. Required: title, board, pot (bb), effective_stack (bb). The job stays pending: solver dispatch and billing are not configured, so this does not start a solve.

  Paramètres, retour & exemple (11)

  Paramètres

  • pot · number · requis
    Starting pot in big blinds.
  • tags · array · optionnel
    Free-form tags stored with the job.
  • board · string · requis
    Board to solve, e.g. "3h 3d 2s".
  • title · string · requis
    Label for the job, 1 to 120 characters.
  • ip_range · string · optionnel
    In-position range in the same weights format.
  • add_allin · boolean · optionnel
    Add an all-in branch alongside the bet sizes.
  • bet_sizes · array · optionnel
    Bet sizes as fractions of the pot, e.g. [0.33, 0.75].
  • oop_range · string · optionnel
    Out-of-position range as hand-class weights, e.g. "AA:1,AKs:0.42". Defaults are left to the solver config.
  • iterations · integer · optionnel
    Requested solver iterations, 50 to 5000.
  • effective_stack · number · requis
    Effective stack behind, in big blinds.
  • max_aggressions · integer · optionnel
    Raises allowed per street, 1 to 4.

  Exemple d'appel

  {"name": "enqueue_solve", "arguments": {"pot": 1, "board": "texte", "title": "texte", "effective_stack": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"pot": 1, "board": "texte", "title": "texte", "reason": "texte", "status": "texte", "dispatch": "texte", "queue_id": 1, "createdAt": "texte", "solution_id": "texte", "effective_stack": 1}}

• explain_combo≈ 1102 tokens

  Preferred tool for exact NLHE postflop hand questions. Returns a canonical context, exact action mix, action EV/loss when available, made-hand and draw classification, blocker facts, and same-rank-class suit comparisons. The server computes evidence; the agent should phrase causality as interpretation.

  Paramètres, retour & exemple (8)

  Paramètres

  • pack · string · requis
    Pack id from list_postflop_packs. Use a sizingTrees packId to pick the tree: the pack id for 75% pot on the flop, or "<pack>-flop33" for 33%.
  • path · array · optionnel
    Exact childSegment path from get_postflop_node, e.g. ["Check", "Bet 5.5"]. Empty for the root.
  • board · string · requis
    Board in spaced form, e.g. "6s 4h 2s"
  • combo · string · requis
    Required exact two-card combo, e.g. As5s
  • anteBb · number · optionnel
    Requested ante in bb. nlmtt8 models a 1bb BB-ante; other positive antes return unsupported coverage.
  • format · string · optionnel · cash | mtt
    Requested poker format. "cash" uses the cash trees. "mtt" is supported only for preflop chip-EV against game nlmtt8; ICM, PKO, and satellite remain unsupported.
  • objective · string · optionnel · solver_ev | chip_ev | icm | pko | satellite
    Requested optimization objective. chip_ev is supported for nlmtt8 preflop. ICM, PKO, and satellite return unsupported coverage.
  • comparisonLimit · number · optionnel
    Maximum same-rank-class suit comparisons (default 6, maximum 12)

  Exemple d'appel

  {"name": "explain_combo", "arguments": {"pack": "texte", "board": "texte", "combo": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "context": {}, "coverage": {}, "warnings": [], "schemaVersion": "texte"}}

• find_hands≈ 2824 tokens

  Find hands the account has uploaded. Returns hand_id, session_id, handAt, position, cards, game, board, potType, street lines, and netBb. Solver grade buckets are not filled. If this account has no hands, offer the hosted upload page from get_upload_link (https://pokerdata.io/upload) instead of asking the user to paste histories into chat.

  Paramètres, retour & exemple (8)

  Paramètres

  • sort · string · requis · recent | biggest_win | biggest_loss
    Row order: newest first, largest win first, or largest loss first (the default).
  • limit · integer · requis
    Hands to return, 1 to 50.
  • filter · ? · optionnel
    Hand-level filters, all optional.
  • game_type · ? · optionnel
    Only hands of this game type. Matches hole-card count.
  • session_id · ? · optionnel
    Only hands from this upload session (see list_my_sessions).
  • table_size · ? · optionnel
    Only hands dealt at tables of this many seats.
  • gto_vs_3bet_bucket · ? · optionnel
    Solver grade bucket for hero's action vs a 3-bet. Grades are not computed, so any value matches nothing rather than inventing a frequency.
  • gto_plo5_rfi_bucket · ? · optionnel
    Solver grade bucket for PLO5 raise-first-in. Grades are not computed, so any value matches nothing.

  Exemple d'appel

  {"name": "find_hands", "arguments": {"sort": "recent", "limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"gto": "texte", "hint": "texte", "hands": [], "total": 1, "gtoNote": "texte", "returned": 1}}

• get_board_report≈ 1330 tokens

  Preferred tool for board-texture heuristics. Aggregates action frequencies and range/action composition across solved boards in one postflop pack. Results explicitly report sample breadth and use equal weight per board.

  Paramètres, retour & exemple (8)

  Paramètres

  • pack · string · requis
    Pack id from list_postflop_packs. Use a sizingTrees packId to pick the tree: the pack id for 75% pot on the flop, or "<pack>-flop33" for 33%.
  • path · array · optionnel
    Exact childSegment path from get_postflop_node, e.g. ["Check", "Bet 5.5"]. Empty for the root.
  • anteBb · number · optionnel
    Requested ante in bb. nlmtt8 models a 1bb BB-ante; other positive antes return unsupported coverage.
  • format · string · optionnel · cash | mtt
    Requested poker format. "cash" uses the cash trees. "mtt" is supported only for preflop chip-EV against game nlmtt8; ICM, PKO, and satellite remain unsupported.
  • filters · object · optionnel
    Texture filters applied to the pack's solved boards. All optional; omit for every board.
  • objective · string · optionnel · solver_ev | chip_ev | icm | pko | satellite
    Requested optimization objective. chip_ev is supported for nlmtt8 preflop. ICM, PKO, and satellite return unsupported coverage.
  • boardLimit · number · optionnel
    Maximum matching boards to analyze (default and maximum 50)
  • representativeLimit · number · optionnel
    Maximum representative boards returned (default 12, maximum 20)

  Exemple d'appel

  {"name": "get_board_report", "arguments": {"pack": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "context": {}, "coverage": {}, "warnings": [], "schemaVersion": "texte"}}

• get_config≈ 844 tokens

  Table for one preflop game and stack, in big blinds: seats, stacks, blinds (sb 0.5, bb 1), ante, antePostedBy, stackIncludesAnte, openSizes (first-in raise-to), evUnit, evBaseline. Convergence is not published. stackIncludesAnte is true: the named depth is the starting stack and the 1bb BB ante is posted from it. openSizes at 40bb is open 2.2x (listing 2.2bb; node decodes code 40034 to 2.19bb) and SB 2.8x (2.8bb). 10bb is all-in/fold versus 50bb stacks, so stacks is null there. evs on nodes are small blinds relative to fold. Example: get_config({ game: "nlmtt8", stack: 40 }).

  Paramètres, retour & exemple (2)

  Paramètres

  • game · string · requis · nl | nl9 | nlmtt8 | nlh8-hydra | plo | plo5 | plo9 | plo6hu
    "nl" = no-limit hold'em 6-max cash (169-grid hands, per-hand EV in small blinds), "nl9" = no-limit hold'em 9-max cash, "nlmtt8" = no-limit hold'em 8-max MTT chip-EV (10–300bb, 1bb BB-ante; Fold/Call/Limp/AI/Open/3B tokens), "nlh8-hydra" = no-limit hold'em 8-max MTT chip-EV with a classic 0.1bb ante from every seat (10, 20, 30, 60bb; same tokens as nlmtt8), "plo" = pot-limit Omaha 6-max cash (4-card), "plo5" = pot-limit Omaha 5-card 6-max (100bb, 1.2bb ante), "plo9" = pot-limit Omaha 9-max cash, "plo6hu" = 6-card Omaha heads-up (BTN vs BB, 100bb). Cash trees are not tournament, ICM, PKO, or satellite solves. nlmtt8 is chip-EV only.
  • stack · number · requis
    Stack depth in big blinds, e.g. 40

  Exemple d'appel

  {"name": "get_config", "arguments": {"game": "nl", "stack": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ante": 1, "game": "texte", "seats": [], "stack": 1, "units": {}, "blinds": {}, "evUnit": "texte", "stacks": [], "openSizes": {}, "evBaseline": "texte", "antePostedBy": "texte", "schemaVersion": 1}}

• get_exploitability≈ 379 tokens

  Preflop exploitability for a game. No preflop dataset publishes exploitability, convergence, or iteration counts. The answer is not available; this tool never fills in a number.

  Paramètres, retour & exemple (1)

  Paramètres

  • game · string · requis
    Preflop game id to report on, e.g. "nl" or "nlmtt8". Any known game answers "not available".

  Exemple d'appel

  {"name": "get_exploitability", "arguments": {"game": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"game": "texte", "reason": "texte", "status": "texte", "dataset": "texte", "available": true, "iterations": 1, "convergence": 1, "exploitability": 1}}

• get_hand_results≈ 459 tokens

  Per-hand cumulative results for a winnings curve. `points` is [{ hand, bb }], oldest to newest, downsampled. Pass session_id for one session. If this account has no hands, offer the hosted upload page from get_upload_link (https://pokerdata.io/upload) instead of asking the user to paste histories into chat.

  Paramètres, retour & exemple (2)

  Paramètres

  • max_points · integer · requis
    Points on the curve after downsampling, 2 to 200.
  • session_id · ? · optionnel
    Only this upload session's hands. Omit for the whole account.

  Exemple d'appel

  {"name": "get_hand_results", "arguments": {"max_points": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "netBb": 1, "points": [], "totalHands": 1}}

• get_node≈ 1231 tokens

  Actions available at a decision node. `history` is an action path ending in the position about to act, e.g. "UTG_60%_HJ". sizeBb is the raise-to in big blinds and sizePctPot is the percent of the pot after calling (nlmtt8 40bb Open 40034 is 2.19bb; the pack label is 2.2x). evs are small blinds relative to fold. Compact mode returns action totals; add `hand` for its exact mixed strategy. full=true is full=1: all 169 hold'em hands with explicit 0, and no invented EVs.

  Paramètres, retour & exemple (7)

  Paramètres

  • full · boolean · optionnel
    Hold'em only. When true, each action includes all 169 hands with weight 0 where the bundle omitted the hand. EVs stay only where the bundle scored them.
  • game · string · requis · nl | nl9 | nlmtt8 | nlh8-hydra | plo | plo5 | plo9 | plo6hu
    "nl" = no-limit hold'em 6-max cash (169-grid hands, per-hand EV in small blinds), "nl9" = no-limit hold'em 9-max cash, "nlmtt8" = no-limit hold'em 8-max MTT chip-EV (10–300bb, 1bb BB-ante; Fold/Call/Limp/AI/Open/3B tokens), "nlh8-hydra" = no-limit hold'em 8-max MTT chip-EV with a classic 0.1bb ante from every seat (10, 20, 30, 60bb; same tokens as nlmtt8), "plo" = pot-limit Omaha 6-max cash (4-card), "plo5" = pot-limit Omaha 5-card 6-max (100bb, 1.2bb ante), "plo9" = pot-limit Omaha 9-max cash, "plo6hu" = 6-card Omaha heads-up (BTN vs BB, 100bb). Cash trees are not tournament, ICM, PKO, or satellite solves. nlmtt8 is chip-EV only.
  • hand · string · optionnel
    Optional hand/class
  • stack · number · requis
    Stack depth in big blinds
  • detail · string · optionnel · compact | full
    Response detail. "compact" is the default and removes bulk maps; use "full" only when exact complete data is required.
  • history · string · requis
    Action path ending in a position
  • minFreq · number · optionnel
    Trim per-action ranges

  Exemple d'appel

  {"name": "get_node", "arguments": {"game": "nl", "stack": 1, "history": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"game": "texte", "hand": "texte", "hint": "texte", "spot": "texte", "actor": "texte", "stack": 1, "units": {}, "evUnit": "texte", "actions": [], "history": "texte", "version": 1, "evBaseline": "texte"}}

• get_opponent_limp_range≈ 772 tokens

  Shown-hand first-in limp range: 169-class counts of hole cards villains showed after an open limp. Pass position for one seat. Sample is showdown-only. This is not a solver range.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · requis
    Hole-card classes to return, most frequent first, 1 to 169.
  • position · ? · optionnel
    Only limps from these seats.
  • game_type · ? · optionnel
    Only hands of this game type.
  • session_id · ? · optionnel
    Only hands from this upload session.
  • table_size · ? · optionnel
    Only hands dealt at tables of this many seats.
  • opponent_id · ? · optionnel
    Only this opponent's limps (see list_my_opponents). Omit for every tracked villain.

  Exemple d'appel

  {"name": "get_opponent_limp_range", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "sample": 1, "classes": [], "classesByPosition": {}}}

• get_opponent_notes≈ 342 tokens

  Leak notes computed from uploaded hands for one opponent, with the sample size on each line.

  Paramètres, retour & exemple (1)

  Paramètres

  • opponent_id · string · requis
    Opponent id from list_my_opponents.

  Exemple d'appel

  {"name": "get_opponent_notes", "arguments": {"opponent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "notes": [], "opponent_id": "texte", "display_name": "texte"}}

• get_postflop_node≈ 1457 tokens

  One postflop solver node: the acting player's strategy for every hand class, the legal next segments, board, reach and the reach-weighted action split. Walk deeper by appending a returned childSegment (an action like "Bet 5.5" or a runout like "deal:7c") to `path`.

  Paramètres, retour & exemple (6)

  Paramètres

  • pack · string · requis
    Pack id from list_postflop_packs. Use a sizingTrees packId to pick the tree: the pack id for 75% pot on the flop, or "<pack>-flop33" for 33%.
  • path · array · optionnel
    Segments from the root, e.g. ["Check", "Bet 5.5"]. Empty for the root node.
  • board · string · requis
    Board in spaced form, e.g. "3h 3d 2s"
  • combo · string · optionnel
    Optional exact combo, e.g. AsKh (PLO5: five cards, as listed in the node's hands)
  • limit · number · optionnel
    Maximum representative compact combos (default 40, maximum 200)
  • detail · string · optionnel · compact | full
    Response detail. "compact" is the default and removes bulk maps; use "full" only when exact complete data is required.

  Exemple d'appel

  {"name": "get_postflop_node", "arguments": {"pack": "texte", "board": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "node": {}, "path": [], "board": "texte", "combo": "texte", "hands": [], "potBb": 1, "reach": [], "actions": [], "columns": [], "summary": {}, "actionFreqs": []}}

• get_postflop_range≈ 1091 tokens

  The range a player takes one flop action with, from a solved pack: hand-class weights ("AA:1,AKs:0.42,...", same format as the preflop ranges) after every earlier flop action on the path. `path` ends in the action whose range you want, e.g. ["Check", "Bet 1.8", "Call 1.8"] for the check-call range. Bet-size tree. "33" = 33% pot on the flop, then 75% pot on the turn and river, plus all-in. "75" = 75% pot on every street, plus all-in. Compact and full detail apply to the other range tools; this returns the action range itself.

  Paramètres, retour & exemple (6)

  Paramètres

  • hand · string · optionnel
    Optional exact combo (AsKh) or hand class (AKs) for one frequency instead of reading the whole range.
  • pack · string · requis
    Pack id from list_postflop_packs
  • path · array · requis
    Flop actions ending in the action whose range you want
  • tree · string · requis · 33 | 75
    Bet-size tree. "33" = 33% pot on the flop, then 75% pot on the turn and river, plus all-in. "75" = 75% pot on every street, plus all-in. PLO5 packs are solved on "33" only.
  • board · string · requis
    Flop, e.g. "3h 3d 2s"
  • minFreq · number · optionnel
    Drop classes at or below this weight. Default 0.

  Exemple d'appel

  {"name": "get_postflop_range", "arguments": {"pack": "texte", "path": [], "tree": "33", "board": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hand": {}, "pack": "texte", "path": [], "tree": "texte", "board": "texte", "error": "texte", "range": "texte", "action": "texte", "summary": {}, "weights": {}}}

• get_queued_solve≈ 398 tokens

  Look up one queued solve for this account. status is pending, running, done, or failed. solution_id is null until a worker exists.

  Paramètres, retour & exemple (1)

  Paramètres

  • queue_id · integer · requis
    Queue id returned by enqueue_solve.

  Exemple d'appel

  {"name": "get_queued_solve", "arguments": {"queue_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"pot": 1, "board": "texte", "title": "texte", "reason": "texte", "status": "texte", "dispatch": "texte", "queue_id": 1, "createdAt": "texte", "solution_id": "texte", "effective_stack": 1}}

• get_range≈ 1396 tokens

  The GTO range for one spot. `spot` is an action path of POSITION_ACTION pairs ending in the action whose range you want, e.g. NLHE cash "UTG_60%_HJ_Call", nlmtt8 "UTG_Open", or PLO "UTG_Open_HJ_3B". Add `hand` for one exact frequency and EV. Compact mode is default; PLO returns representative pure/mixed hands unless a hand is specified; plo5 returns the top hands by EV that take the action (limit up to 500 compact, 2000 full).

  Paramètres, retour & exemple (7)

  Paramètres

  • game · string · requis · nl | nl9 | nlmtt8 | nlh8-hydra | plo | plo5 | plo9 | plo6hu
    "nl" = no-limit hold'em 6-max cash (169-grid hands, per-hand EV in small blinds), "nl9" = no-limit hold'em 9-max cash, "nlmtt8" = no-limit hold'em 8-max MTT chip-EV (10–300bb, 1bb BB-ante; Fold/Call/Limp/AI/Open/3B tokens), "nlh8-hydra" = no-limit hold'em 8-max MTT chip-EV with a classic 0.1bb ante from every seat (10, 20, 30, 60bb; same tokens as nlmtt8), "plo" = pot-limit Omaha 6-max cash (4-card), "plo5" = pot-limit Omaha 5-card 6-max (100bb, 1.2bb ante), "plo9" = pot-limit Omaha 9-max cash, "plo6hu" = 6-card Omaha heads-up (BTN vs BB, 100bb). Cash trees are not tournament, ICM, PKO, or satellite solves. nlmtt8 is chip-EV only.
  • hand · string · optionnel
    Optional hand/class, e.g. AKs or (KA)(KA)
  • spot · string · requis
    Action path ending in an action
  • limit · number · optionnel
    Maximum compact rows to return (default 120, maximum 500).
  • stack · number · requis
    Stack depth in big blinds, e.g. 100
  • detail · string · optionnel · compact | full
    Response detail. "compact" is the default and removes bulk maps; use "full" only when exact complete data is required.
  • minFreq · number · optionnel
    Drop hands at or below this weight (PLO ranges are large)

  Exemple d'appel

  {"name": "get_range", "arguments": {"game": "nl", "spot": "texte", "stack": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ev": 1, "evs": {}, "evSb": 1, "freq": 1, "game": "texte", "hand": "texte", "hint": "texte", "kind": "texte", "spot": "texte", "actor": "texte", "hands": 1, "range": []}}

• get_range_metadata≈ 752 tokens

  Index metadata for one preflop game, stack, and path: bundle stats for hold'em/PLO bundles, or the matching node row for plo5 and plo6hu. Does not return a strategy and does not invent exploitability.

  Paramètres, retour & exemple (3)

  Paramètres

  • game · string · requis
    Preflop game id, e.g. "nl", "nl9", "nlmtt8", "nlh8-hydra", "plo", "plo9", "plo5", "plo6hu".
  • path · string · requis
    Action path, e.g. UTG_Open or LJ_Fold. Use (root) or empty for the plo5 root.
  • stack · number · requis
    Stack depth in big blinds, e.g. 100.

  Exemple d'appel

  {"name": "get_range_metadata", "arguments": {"game": "texte", "path": "texte", "stack": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"game": "texte", "note": "texte", "path": "texte", "rows": [], "actor": "texte", "error": "texte", "match": "texte", "stack": 1, "dataset": "texte", "preflopExploitability": "texte"}}

• get_session_summary≈ 641 tokens

  One uploaded session's headline numbers: hero, game type, start and end times, hands played, net result in big blinds, and HUD rates (VPIP, PFR, 3-bet, open limp) as percentages with the sample size. Use it after list_my_sessions to report how a session went; use get_hand_results for its winnings curve and find_hands for individual hands. Returns an error for an unknown session id. Any key works, free trial included, and it never counts against the allowance. If this account has no hands, offer the hosted upload page from get_upload_link (https://pokerdata.io/upload) instead of asking the user to paste histories into chat.

  Paramètres, retour & exemple (1)

  Paramètres

  • session_id · string · requis
    Session id from list_my_sessions.

  Exemple d'appel

  {"name": "get_session_summary", "arguments": {"session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "hud": {}, "hero": "texte", "error": "texte", "hands": 1, "netBb": 1, "endedAt": "texte", "game_type": "texte", "startedAt": "texte"}}

• get_started≈ 569 tokens

  Start here with a new user. Returns the short set of questions to ask them (game, format, stakes, goal), a menu of what PokerData can do with the tools for each, what is free without a key, and how to file a feature or data request. Free, no key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_started", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"access": {}, "requests": {}, "signedIn": true, "askTheUser": {}, "notCovered": "texte", "capabilities": []}}

• get_tournament_results≈ 582 tokens

  MTT results imported from tournament summary files. Money is in cents. Hand histories are not a source of buy-ins or prizes. If this account has no hands, offer the hosted upload page from get_upload_link (https://pokerdata.io/upload) instead of asking the user to paste histories into chat.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · requis
    Tournament summaries to include, 1 to 500.

  Exemple d'appel

  {"name": "get_tournament_results", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"roi": 1, "note": "texte", "itmPct": 1, "recent": [], "buyInCents": 1, "tournaments": 1, "receivedCents": 1, "netProfitCents": 1}}

• get_tree_docs≈ 776 tokens

  Tree documentation for one dataset: coverage note from the shipped README and per-stack bundle or node counts from the shipped index. Does not read or modify range bytes.

  Paramètres, retour & exemple (1)

  Paramètres

  • dataset · string · requis
    Dataset id from list_datasets, e.g. "nl/v2", "nl9", "nlmtt8", "plo", "plo9", "plo5", "plo6hu".

  Exemple d'appel

  {"name": "get_tree_docs", "arguments": {"dataset": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "source": "texte", "stacks": [], "dataset": "texte", "coverage": "texte", "preflopExploitability": "texte"}}

• get_upload_link≈ 296 tokens

  Primary hand-upload path. Returns https://pokerdata.io/upload on this origin, with a short-lived signed token for the caller's account when signing is configured. Hand the URL to the user. Pasting histories into chat is the fallback.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_upload_link", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "primary": true, "resource": "texte", "expiresAt": "texte", "tokenAttached": true}}

• list_datasets≈ 474 tokens

  List preflop datasets in the shipped tree documentation (stacks, positions, whether each bundle was analyzed). Preflop exploitability is not available.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_datasets", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"readme": "texte", "source": "texte", "datasets": [], "generated": "texte", "preflopExploitability": "texte"}}

• list_games≈ 826 tokens

  Discover covered stack depths and positions. Call this before low-level preflop queries. "nl" = no-limit hold'em 6-max cash (169-grid hands, per-hand EV in small blinds), "nl9" = no-limit hold'em 9-max cash, "nlmtt8" = no-limit hold'em 8-max MTT chip-EV (10–300bb, 1bb BB-ante; Fold/Call/Limp/AI/Open/3B tokens), "nlh8-hydra" = no-limit hold'em 8-max MTT chip-EV with a classic 0.1bb ante from every seat (10, 20, 30, 60bb; same tokens as nlmtt8), "plo" = pot-limit Omaha 6-max cash (4-card), "plo5" = pot-limit Omaha 5-card 6-max (100bb, 1.2bb ante), "plo9" = pot-limit Omaha 9-max cash, "plo6hu" = 6-card Omaha heads-up (BTN vs BB, 100bb). Cash trees are not tournament, ICM, PKO, or satellite solves. nlmtt8 is chip-EV only.

  Paramètres, retour & exemple (1)

  Paramètres

  • detail · string · optionnel · compact | full
    Response detail. "compact" is the default and removes bulk maps; use "full" only when exact complete data is required.

  Exemple d'appel

  {"name": "list_games", "arguments": {"detail": "compact"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"_coverage": {}}}

• list_library_solutions≈ 232 tokens

  Finished postflop solutions saved for this account. None are marked done while dispatch is disabled.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · requis
    Solutions to return, 1 to 50.

  Exemple d'appel

  {"name": "list_library_solutions", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "solutions": []}}

• list_my_opponents≈ 723 tokens

  Tracked opponents from uploaded hands. Each row has handCount, handsVsHero, and heroBb100Vs. Pass name to find one villain.

  Paramètres, retour & exemple (6)

  Paramètres

  • hero · ? · optionnel
    Only hands where this hero name was seated.
  • name · ? · optionnel
    Case-insensitive substring of the opponent's screen name.
  • sort · string · requis · hands | last_seen | toughest | softest
    Row order: most hands, most recent, or by hero's bb/100 against them (toughest = worst for hero).
  • limit · integer · requis
    Opponents to return, 1 to 500.
  • game_type · ? · optionnel
    Only hands of this game type, e.g. "NLHE" or "PLO".
  • min_hands · integer · requis
    Drop opponents seen in fewer hands than this.

  Exemple d'appel

  {"name": "list_my_opponents", "arguments": {"sort": "hands", "limit": 1, "min_hands": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"opponents": []}}

• list_my_requests≈ 356 tokens

  List the feature and data requests this account has filed, newest first, with their status. Free with any key.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Maximum requests to return (default 20, maximum 100).

  Exemple d'appel

  {"name": "list_my_requests", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"requests": []}}

• list_my_sessions≈ 499 tokens

  Recent uploaded sessions, newest first: id, hero, game type, dates, hands, and net result. game_type matches hole-card count. If this account has no hands, offer the hosted upload page from get_upload_link (https://pokerdata.io/upload) instead of asking the user to paste histories into chat.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · requis
    Sessions to return, 1 to 50.
  • game_type · ? · optionnel
    Only sessions containing this game type.

  Exemple d'appel

  {"name": "list_my_sessions", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "sessions": []}}

• list_postflop_packs≈ 1220 tokens

  Every solved postflop pack: preflop line, positions (OOP vs IP), stack, pot, the bet-size trees it is solved under, and the solved boards. Boards use the spaced form ("3h 3d 2s"). NLHE packs list `sizingTrees`: "75" (75% pot every street, the pack id itself) and "33" (33% pot on the flop, then 75%, under the `<pack>-flop33` id); every postflop tool accepts either tree's packId. PLO5 packs (ids starting plo5-) solve one 33% flop tree, flop decisions only. Compact output lists board names per pack. Pass `pack` (the 75% id or the -flop33 id) for that tree's per-board detail and per-flop exploitability where the index publishes a number. Missing exploitability is omitted, never estimated. Pass `variant` to list only NLHE or PLO5 packs. Call this before get_postflop_node.

  Paramètres, retour & exemple (3)

  Paramètres

  • pack · string · optionnel
    One pack id (75% id or the -flop33 id): per-board detail and that tree's exploitability
  • detail · string · optionnel · compact | full
    Response detail. "compact" is the default and removes bulk maps; use "full" only when exact complete data is required.
  • variant · string · optionnel · nlhe | plo5
    Only packs of this game: nlhe (hold'em) or plo5 (five-card Omaha)

  Exemple d'appel

  {"name": "list_postflop_packs", "arguments": {"pack": "texte", "detail": "compact", "variant": "nlhe"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "packs": []}}

• list_queued_solves≈ 436 tokens

  List this account's solver-queue jobs, newest first. Jobs are not dispatched.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · requis
    Jobs to return, 1 to 50.

  Exemple d'appel

  {"name": "list_queued_solves", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"solves": []}}

• list_spots≈ 809 tokens

  Search valid decision nodes for a stack depth, tagged by depth (1 = RFI, 2 = vs open, 3 = 3-bet pots, …). Compact mode is paginated; use depth, contains, and offset to narrow results without loading thousands of paths. plo9 has no spot index: walk it with get_node from history "UTG".

  Paramètres, retour & exemple (7)

  Paramètres

  • game · string · requis · nl | nl9 | nlmtt8 | nlh8-hydra | plo | plo5 | plo9 | plo6hu
    "nl" = no-limit hold'em 6-max cash (169-grid hands, per-hand EV in small blinds), "nl9" = no-limit hold'em 9-max cash, "nlmtt8" = no-limit hold'em 8-max MTT chip-EV (10–300bb, 1bb BB-ante; Fold/Call/Limp/AI/Open/3B tokens), "nlh8-hydra" = no-limit hold'em 8-max MTT chip-EV with a classic 0.1bb ante from every seat (10, 20, 30, 60bb; same tokens as nlmtt8), "plo" = pot-limit Omaha 6-max cash (4-card), "plo5" = pot-limit Omaha 5-card 6-max (100bb, 1.2bb ante), "plo9" = pot-limit Omaha 9-max cash, "plo6hu" = 6-card Omaha heads-up (BTN vs BB, 100bb). Cash trees are not tournament, ICM, PKO, or satellite solves. nlmtt8 is chip-EV only.
  • depth · number · optionnel
    Optional decision depth filter
  • limit · number · optionnel
    Maximum compact rows to return (default 120, maximum 500).
  • stack · number · requis
    Stack depth in big blinds
  • detail · string · optionnel · compact | full
    Response detail. "compact" is the default and removes bulk maps; use "full" only when exact complete data is required.
  • offset · number · optionnel
    Compact pagination offset
  • contains · string · optionnel
    Optional case-insensitive history substring filter

  Exemple d'appel

  {"name": "list_spots", "arguments": {"game": "nl", "stack": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"game": "texte", "hint": "texte", "spots": [], "stack": 1, "total": 1, "offset": 1, "matched": 1, "returned": 1, "nextOffset": 1}}

• submit_request≈ 547 tokens

  File a feature request or data request for the user, after telling them their question isn't covered and they agree. kind "data" is missing coverage (a game, format, stack depth, spot, or solve); kind "feature" is a missing capability (a tool, filter, export, or endpoint). Free with any key; the PokerData team reads every one.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · requis · feature | data
    "data" for missing coverage, "feature" for a missing capability.
  • details · string · optionnel
    Anything else that helps: game, format, stakes, stack depths, positions, how they would use it.
  • summary · string · requis
    One line saying what the user wants, e.g. "9-max MTT preflop at 25bb with ICM".
  • question · string · optionnel
    The user's original question that couldn't be answered, verbatim if possible.

  Exemple d'appel

  {"name": "submit_request", "arguments": {"kind": "feature", "summary": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"message": "texte", "request": {}}}

• upload_hand_history≈ 395 tokens

  Secondary upload path for a small paste. Prefer get_upload_link and the hosted /upload page. Runs the same ingestion pipeline and returns hands parsed, tournaments parsed, and errors. Does not grade solver frequencies.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Raw hand history or tournament summary text.
  • filename · string · optionnel
    Name to record for the paste. Defaults to "paste.txt".

  Exemple d'appel

  {"name": "upload_hand_history", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"errors": [], "filename": "texte", "persisted": true, "sessionId": "texte", "handsParsed": 1, "persistence": "texte", "tournamentsParsed": 1}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://pokerdata.io/api/mcp