Sudoku Play
A playable 9x9 Sudoku engine with uniquely-solvable generation and real logical hints
How cooperative board games work — shared win conditions, difficulty scaling, quarterbacking, and hidden-traitor hybrids
Unify Dynamics LLC
Real questions, and the tools your agent calls to answer them.
mechanic_infodesign_considerationterm_glossarygame_examplesdifficulty_scaling_explainerfind_game_for_groupcategory_listbeginner_tipsCoop is a fully local, hand-curated reference on how cooperative board/card games work as a genre. mechanic_info explains one named mechanic in full: shared win/loss conditions, escalating difficulty tracks, AI/automa decks, real-time pressure, hidden-hand information rules, communication and hint-token restrictions, shared action pools, asymmetric player powers, hidden-traitor roles, semi-cooperative private objectives, delayed betrayal triggers, and more. design_consideration explains a design-level issue in depth: the alpha-player problem, concrete quarterbacking mitigation techniques, difficulty scaling as a design goal, how much information to hide from teammates, avoiding player elimination, when to reveal a hidden traitor, the tradeoff of restricting communication, and solo-mode design. term_glossary defines genre vocabulary. game_examples finds real, published cooperative games that use a named mechanic or fall into a named subgenre category, described factually without reproducing any game's rules text. difficulty_scaling_explainer explains one specific difficulty-scaling system and which direction makes it easier or harder. find_game_for_group suggests a format for any player count, from solo/automa play to party scale. category_list gives eight subgenre category archetypes with real example games. beginner_tips gives an ordered shortlist of practical tips for playing cooperative games well. Keyless; fully local; zero upstream calls; nothing stored.
Sources: Original, hand-curated reference on how cooperative board/card games work as a genre, with real published games cited factually as examples; fully local, zero upstream calls
The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.
8 tools, grouped by job. Every one is read-only or compute-only.
https://coop.connectorbay.com/mcpA playable 9x9 Sudoku engine with uniquely-solvable generation and real logical hints
A real, playable rhombus-board connection game with a shortest-bridge AI opponent
A real, playable Kalah-rules sowing game with a minimax + alpha-beta AI opponent
A real, playable 5-in-a-row connection game with a threat-based AI opponent
A real, playable flip-and-capture board game with a minimax + alpha-beta AI opponent
A real, playable American-checkers engine with a minimax + alpha-beta AI opponent
https://coop.connectorbay.com/mcpPOST https://coop.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://coop.connectorbay.com/openapi.jsonAuthorization: Bearer <key> raises rate limits.https://coop.connectorbay.com/health · Tool schemas: https://coop.connectorbay.com/tools.jsonHow cooperative board games work — shared win conditions, difficulty scaling, quarterbacking, and hidden-traitor hybrids.
Coop is a fully local, hand-curated reference on how cooperative board/card games work as a genre. mechanic_info explains one named mechanic in full: shared win/loss conditions, escalating difficulty tracks, AI/automa decks, real-time pressure, hidden-hand information rules, communication and hint-token restrictions, shared action pools, asymmetric player powers, hidden-traitor roles, semi-cooperative private objectives, delayed betrayal triggers, and more. design_consideration explains a design-level issue in depth: the alpha-player problem, concrete quarterbacking mitigation techniques, difficulty scaling as a design goal, how much information to hide from teammates, avoiding player elimination, when to reveal a hidden traitor, the tradeoff of restricting communication, and solo-mode design. term_glossary defines genre vocabulary. game_examples finds real, published cooperative games that use a named mechanic or fall into a named subgenre category, described factually without reproducing any game's rules text. difficulty_scaling_explainer explains one specific difficulty-scaling system and which direction makes it easier or harder. find_game_for_group suggests a format for any player count, from solo/automa play to party scale. category_list gives eight subgenre category archetypes with real example games. beginner_tips gives an ordered shortlist of practical tips for playing cooperative games well. Keyless; fully local; zero upstream calls; nothing stored.
Not an official product of, or affiliated with, any brand, league, publisher, or organization it may factually mention. Coop is a hand-curated reference and design tool, not a substitute for an official rulebook, certified instruction, or professional advice. Fully local, zero upstream calls, nothing stored.
mechanic_info — Full explanation of one cooperative-genre mechanic: how it works step by step, and why it matters for a designer or a table. Covers shared win/loss conditions, escalating difficulty, AI/automa decks, real-time pressure, information-sharing rules, hidden-traitor and semi-cooperative mechanics, and more. Use for "how does the escalation deck work", "what is a shared action pool", "how does a hidden traitor role work". Args: name.
term_glossary — Definitions of cooperative-genre vocabulary — quarterbacking, alpha player, hive mind, threat track, escalation deck, AI deck/automa, hidden traitor, semi-cooperative, rubber-banding, total party loss, and more. Use for "what does quarterbacking mean", "what's the difference between hidden traitor and semi-cooperative". Args: term.
design_consideration — In-depth discussion of one cooperative-game design issue: the alpha-player problem, concrete quarterbacking mitigation techniques, difficulty scaling as a design goal, how much information to hide from teammates, avoiding player elimination, when to reveal a hidden traitor, the tradeoff of restricting communication, or solo-mode design. Use for "how do we stop one player from quarterbacking", "what's the alpha player problem", "when should a hidden traitor be revealed". Args: topic.
difficulty_scaling_explainer — Explains one specific difficulty-scaling system used across cooperative games — an escalation deck/threat track, an adaptive AI/automa opponent, preset difficulty levels, player-count scaling, rubber-banding/dynamic difficulty, real-time timer pressure, or legacy/campaign difficulty ramp — and which direction makes it easier or harder. Use for "how does an escalation deck work", "how should difficulty scale by player count", "what is rubber-banding difficulty". Args: topic.
game_examples — Finds real, published cooperative games that use a named mechanic (e.g. "hidden traitor role") or fall into a named subgenre category (e.g. "real-time cooperative"), each with a short factual description. No game's actual rules text, card text, or card art is reproduced — only factual, original descriptions of what the game does. Use for "what games use a hidden traitor mechanic", "give me examples of real-time cooperative games", "what games have an escalating difficulty deck". Args: mechanic.
category_list — Eight subgenre category archetypes for cooperative games — full cooperative, semi-cooperative, hidden- traitor hybrid, real-time, cooperative trick-taking, legacy/campaign, solo-compatible, and party-scale — each with a description and real example games. Use for "what subgenres of cooperative games are there", "what's the difference between semi-cooperative and hidden-traitor games".
find_game_for_group — Suggests a suitable cooperative-game format and concrete adjustments for a given player count, from solo/ automa play through the classic 3-4 player sweet spot to party-scale real-time formats for 7+, with real example games at each size. Use for "what cooperative game format works for 6 players", "can cooperative games work solo". Args: player_count.
beginner_tips — An ordered shortlist of practical tips for playing cooperative games well — how to avoid quarterbacking, how to handle a hidden-traitor accusation, how to track an escalating threat track together. Use for "what should a beginner know about co-op games", "tips for playing cooperative board games well". Args: count.
ok: true with data, or ok: false with a structured error (bad_input, not_found, upstream_error). degraded lists optional sources that were unreachable.Retry-After. initialize and tools/list are never counted.agent@connectorbay.com · connectorbay.com/coop/support
Effective 25 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.
What Coop is. Coop is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for how cooperative board games work — shared win conditions, difficulty scaling, quarterbacking, and hidden-traitor hybrids. You interact with your assistant; the assistant sends us only the arguments needed for that one lookup.
What we receive. The arguments of each tool call, the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.
Everything is answered from a bundled, hand-curated reference file and nothing is stored. No request is forwarded to any third party — there is no upstream call at all, live or otherwise — and no query is logged in request bodies, recorded, or used to train anything.
What we do not receive or store. We do not receive your conversation with the assistant or your name, and we do not build a profile from your queries: each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.
Sub-processors. None — the entire dataset is bundled with the server and answered locally. Hosting: Vercel (United States regions).
Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.
Children. Coop is a general-audience service operated by the adult using the assistant.
Changes. We will post changes here with a new effective date.
Effective 25 September 2026. These terms govern use of the Coop connector ("the Service") operated by Unify Dynamics LLC ("we", "us").
Email agent@connectorbay.com. We answer within two business days.
https://coop.connectorbay.com/mcphttps://coop.connectorbay.com/openapi.jsonWhen you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Coop never asks for them.