Skip to main content
Glama
261,244 tools. Last updated 2026-07-05 12:05

"A tool or guide for creating a memory card game" matching MCP tools:

  • Replay ordered tower events for a single (firm, game) pair. WHAT IT DOES: GETs /v1/replay/firm/:firm/game/:game. Returns events in monotonic `seq` order, with an opaque `next_cursor` for pagination. Read only, no auth required. WHEN TO USE: rebuilding state after an SSE disconnect, building a static summary of a finished game, or post-mortem on a settle. Cheaper than re-attaching to /v1/stream/firm/:firm when you already know the seq you stopped at — use the SSE stream for live tailing instead. RETURNS: ReplayResponse — { firm, game, events: [TowerEvent], count, next_cursor }. Each TowerEvent has { seq, ts (unix ms), type, firm, game, agent_wallet, data }. PAGINATION: pass the previous response's `next_cursor` as `cursor`. When `next_cursor` is null you've reached head of stream. RELATED: tower_floors (current snapshot), firm_ingest (publish events).
    Connector
  • Generate an AI image and place it directly on a user's Avocado AI flow (the Flows Director). Drops a 'Generating...' tile on the flow immediately, then swaps it for the final image when generation completes (10-60s). It appears live on the open canvas and in the Director Library, grouped by role. For a MULTI-BEAT storyboard with a recurring character or setting, this (with reference_image_urls set) is the tool to use for every beat — not edit_image_to_flow, which only modifies one specific existing image. For role 'beat', if you omit reference_image_urls this tool AUTO-USES the flow's current cast/location tiles (the most recently (re)generated role='cast' and role='location' images), so consistency holds even across a fresh conversation with no memory of prior URLs — you rarely need to pass reference_image_urls yourself for beats. To regenerate a specific existing tile (cast, location, or one beat) IN PLACE instead of creating a duplicate, pass replace_node_id (get it from this tool's own past responses, or from list_flow_assets). Costs match generate_image (1-4 credits per image depending on model and quality).
    Connector
  • Replay ordered tower events for a single (firm, game) pair. WHAT IT DOES: GETs /v1/replay/firm/:firm/game/:game. Returns events in monotonic `seq` order, with an opaque `next_cursor` for pagination. Read only, no auth required. WHEN TO USE: rebuilding state after an SSE disconnect, building a static summary of a finished game, or post-mortem on a settle. Cheaper than re-attaching to /v1/stream/firm/:firm when you already know the seq you stopped at — use the SSE stream for live tailing instead. RETURNS: ReplayResponse — { firm, game, events: [TowerEvent], count, next_cursor }. Each TowerEvent has { seq, ts (unix ms), type, firm, game, agent_wallet, data }. PAGINATION: pass the previous response's `next_cursor` as `cursor`. When `next_cursor` is null you've reached head of stream. RELATED: tower_floors (current snapshot), firm_ingest (publish events).
    Connector
  • Returns the complete 78-card Rider-Waite-Smith deck with full metadata. Each card includes id (slug), name, arcana_type (major/minor), suit, number, element, astrology_correspondence, upright and reversed meanings, keywords for both orientations, yes/no polarity, and visual description. SECTION: WHAT THIS TOOL COVERS The complete 78-card Rider-Waite-Smith deck as structured JSON. Every card includes both upright and reversed meanings as separate fields, making orientation-aware interpretation automatic — the caller does not need to branch on is_reversed. The visual description field describes the imagery of each card. Use this endpoint to populate card databases, build card browsers, filter by element or astrology correspondence, or batch-load the deck for offline use. SECTION: WORKFLOW BEFORE: None — standalone catalogue endpoint. AFTER: asterwise_draw_tarot_cards or asterwise_get_tarot_three_card_spread — use card data from this endpoint to build enriched display layers. SECTION: INPUT CONTRACT response_format — Required: markdown | json (same as all Asterwise tools). No other parameters. SECTION: OUTPUT CONTRACT data[] — 78 card objects, each: id (slug e.g. 'the-fool', 'ace-of-wands') name, arcana_type, suit (null for major arcana), number element, astrology_correspondence keywords_upright[], keywords_reversed[] upright_meaning, reversed_meaning yes_no ('yes'|'no'|'maybe'), description SECTION: RESPONSE FORMAT response_format=json serialises the complete 78-card array as indented JSON. response_format=markdown renders a structured human-readable card catalogue. Both modes return identical underlying data. SECTION: COMPUTE CLASS FAST_LOOKUP — data is static; no ephemeris or randomness involved. SECTION: ERROR CONTRACT INVALID_PARAMS (local): None — no input parameters beyond response_format. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_tarot_major_arcana — returns only the 22 Major Arcana subset. asterwise_get_tarot_suit — returns only the 14 cards of a single suit. asterwise_draw_tarot_cards — returns a random draw, not the catalogue.
    Connector
  • Returns a deterministic daily tarot card seeded by SHA-256 hash of the date string. The same card is returned for all callers on the same date — this is intentional. The daily card is not a reading for an individual but a collective daily energy. SECTION: WHAT THIS TOOL COVERS Deterministic daily oracle: one card with its upright or reversed orientation (also deterministic when allow_reversed=true). The SHA-256 seed ensures that no two consecutive days produce the same card except by mathematical coincidence. The active_meaning field pre-computes the correct interpretation for the orientation — callers do not need to branch on is_reversed. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_tarot_three_card_spread — for deeper daily reading context. SECTION: INPUT CONTRACT date (optional string YYYY-MM-DD) — Date to get the card for. Defaults to today. Example: '2026-05-01' allow_reversed (optional bool) — Default: false. When true: reversed state is also deterministic (seeded by date+'_rev'). When false: card is always upright regardless of date. SECTION: OUTPUT CONTRACT data.date (string — YYYY-MM-DD, the date this card represents) data.card — full card object (same shape as asterwise_get_tarot_card) data.is_reversed (bool) data.active_meaning (string — upright_meaning when not reversed, reversed_meaning when reversed) data.active_keywords[] (string array — upright or reversed keywords per orientation) SECTION: RESPONSE FORMAT response_format=json — full card object with metadata. response_format=markdown — human-readable daily card report. SECTION: COMPUTE CLASS FAST_LOOKUP — deterministic, no randomness. SECTION: ERROR CONTRACT INVALID_PARAMS (local): None — date is validated upstream. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_draw_tarot_cards — random draw, different every call. asterwise_get_tarot_three_card_spread — positional reading with question context.
    Connector
  • Draws N unique random cards from the 78-card deck using cryptographic randomness (Python secrets.SystemRandom). Every call is independent — there is no session state. SECTION: WHAT THIS TOOL COVERS Random card selection for open readings, single-card daily pulls, or custom spread layouts. Uniqueness is guaranteed within a single draw — the same card cannot appear twice in one draw. The active_meaning field is pre-computed per orientation so callers do not need to branch on is_reversed. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: None — interpret drawn cards using their active_meaning and active_keywords fields. SECTION: INPUT CONTRACT count (int 1–78, default 1) — Number of unique cards to draw. Example: 1 (daily pull), 3 (simple reading), 10 (Celtic Cross), 78 (full deck shuffle). Values outside 1–78 are rejected locally with MCP INVALID_PARAMS. allow_reversed (bool, default false) — When true, each drawn card independently has a 50% chance of reversal (cryptographically random, not seeded). SECTION: OUTPUT CONTRACT data.cards[] — array of count objects, each: card — full card object (same shape as asterwise_get_tarot_card) is_reversed (bool) active_meaning (string — orientation-appropriate interpretation) active_keywords[] (string array) position (null — no position for free draws; use spread endpoints for positional reads) position_meaning (null) data.count (int — echoed) data.allow_reversed (bool — echoed) SECTION: RESPONSE FORMAT response_format=json — structured draw result. response_format=markdown — human-readable card report. Both modes return identical underlying data. SECTION: COMPUTE CLASS FAST_LOOKUP — cryptographic randomness, no ephemeris. SECTION: ERROR CONTRACT INVALID_PARAMS (local): — count < 1 or count > 78 → MCP INVALID_PARAMS immediately. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_tarot_card_of_the_day — deterministic daily card, same for all callers. asterwise_get_tarot_three_card_spread — positional read with named positions and meanings. asterwise_get_tarot_celtic_cross — 10-card positional spread.
    Connector

Matching MCP Servers

Matching MCP Connectors

  • Manage your Canvas coursework with quick access to courses, assignments, and grades. Track upcomin…

  • One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.

  • Use when you already have an exact approved pet slug and need the sanitized public pet card, asset URLs, page URL, and install command for that one pet. Use search_pets first when you only have a name/query or need multiple results. Do not use for focused install, badge, embed, card, or request workflow details; use the matching get_* tool instead.
    Connector
  • Move (rename) a memory file from `old_path` to `new_path`. Both paths must stay under `/memories/`; `new_path` must not already exist. The file_cid is preserved (no re-sign) so the prior receipt still binds the bytes. Mirrors the `rename` verb in Anthropic's context-management-2025-06-27 memory tool spec. When to use: Call when the LLM wants to rename or move a memory file. Failure modes: source missing, destination already exists, path escapes `/memories/`.
    Connector
  • USE THIS to check a payment card number's structure before using it — never assume a card number is valid or guess its brand. Verifies the Luhn checksum, detects the brand (Visa, Mastercard, Amex, Discover, Diners, JCB, UnionPay) from its BIN, and checks the length. Does NOT check whether the card is real, active or has funds.
    Connector
  • Validate a credit/debit card number (keyless, offline): Luhn (mod-10) checksum, detected card network (Visa/Mastercard/Amex/Discover/JCB/Diners/UnionPay/Maestro), and whether the length is valid for that network. Spaces/dashes are ignored. NOTE: this checks the number is well-formed — it does NOT verify the card is real/active/funded (that needs a payment processor).
    Connector
  • Create a temporary JSON database (24h TTL, no signup, no keys). Returns the db URL — the only credential — plus admin URL, limits and expiry. Create once per project/task, persist the db URL immediately (local ~/.tmpstate/credentials, project README, and your memory), and reuse it instead of creating again. For retries or parallel workers, pass a stable idempotency_key so duplicate calls return the same database.
    Connector
  • Create a page in a space (editor+). Body is markdown; tela://page/{id} links and [[Page Title]] wikilinks (resolved by title within the space) are indexed as backlinks. tela renders a rich block palette beyond plain markdown — to-do list, pull quote, callout, collapsible, tabs, kanban board, stat grid, timeline, calendar, poll, chart, embed, mermaid diagram, image, file attachment, code block, equation, inline math, table, highlight, wikilink, footnote. Prefer these over walls of text; read the tela://authoring-guide resource (or this server's instructions) for exact syntax. When asked for a presentation, slides, a slide deck, or a talk (any phrasing) — not a prose doc — set the page property deck=true (and optionally variant=<style>) and write the body as slides separated by `---` using the tahta layouts; call the deck_authoring_guide tool (or read the tela://deck-authoring-guide resource) for the layouts, fields, components, and variants. When asked for a spreadsheet, a table of data with formulas/totals, a budget, a tracker, or any grid that computes — not a prose doc — set the page property sheet=true and write the body as Defter markdown (compact GFM tables + an optional ```defter-style block); call the sheet_authoring_guide tool (or read the tela://sheet-authoring-guide resource) for the format, formulas, and styling.
    Connector
  • ⚠️ MANDATORY FIRST STEP - Call this tool BEFORE using any other Canvs tools! Returns comprehensive instructions for creating whiteboards: tool selection strategy, iterative workflow, and examples. Following these instructions ensures correct diagrams.
    Connector
  • [ChatGPT Connector compat] Fetch memory by ID. Exists to satisfy ChatGPT Deep Research's required `search`/`fetch` tool contract. Native MCP clients should fetch via `recall` + memory_id, or use the API's GET /memories/{id} endpoint directly. Returns a single memory with citation support (id, title, url, text fields). Args: id: Memory UUID to fetch ctx: MCP context Returns: Dict with id, title, url, text, metadata fields
    Connector
  • Draws one card and returns a yes, no, or maybe answer with confidence level. The answer is derived from the card's built-in yes_no polarity and its orientation. SECTION: WHAT THIS TOOL COVERS Quick binary oracle using the classical tarot yes/no system. Each card in the Rider-Waite-Smith deck has a pre-assigned polarity (yes/no/maybe). Reversal introduces uncertainty — a yes-polarity card reversed becomes maybe rather than no. This allows nuanced answers: strong yes, leaning toward yes, leaning toward no, strong no, or genuinely unclear. Answer logic (exact): yes-polarity card + upright → answer='yes', confidence='strong' yes-polarity card + reversed → answer='maybe', confidence='leaning' no-polarity card + upright → answer='no', confidence='strong' no-polarity card + reversed → answer='maybe', confidence='leaning' maybe-polarity card (any orientation) → answer='maybe', confidence='unclear' SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_tarot_three_card_spread — for more context when the yes/no answer is 'maybe' or the situation needs elaboration. SECTION: INPUT CONTRACT allow_reversed (bool, default true) — Recommended to keep true for nuanced answers. Set false only if you want strictly yes/no with no maybe results from reversal. question (optional string, max 500 chars) — The yes/no question being asked. Example: 'Should I accept this job offer?' Example: 'Will the project launch on time?' SECTION: OUTPUT CONTRACT data.card — full card object data.is_reversed (bool) data.answer (string — 'yes'|'no'|'maybe') data.confidence (string — 'strong' when card directly says yes/no; 'leaning' when reversed card; 'unclear' when maybe-polarity card) data.active_meaning (string — orientation-appropriate interpretation) data.question (string or null — echoed) SECTION: RESPONSE FORMAT response_format=json — full yes/no result object. response_format=markdown — formatted oracle response. SECTION: COMPUTE CLASS FAST_LOOKUP — cryptographic randomness, no ephemeris. SECTION: ERROR CONTRACT INVALID_PARAMS (local): None. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_tarot_three_card_spread — positional reading, not binary answer. asterwise_draw_tarot_cards — free draw without answer logic.
    Connector
  • SECOND STEP in the troubleshooting workflow. Read the full content and solution of a specific Knowledge Base card. Returns the card content WITH reliability metrics and related cards so you can assess trustworthiness and explore connected issues. WHEN TO USE: - Call this ONLY after obtaining a valid `kb_id` from the `resolve_kb_id` tool. INPUT: - `kb_id`: The exact ID of the card (e.g., 'CROSS_DOCKER_001'). OUTPUT: - Returns reliability metrics followed by the full Markdown content of the card, plus related cards. - You MUST apply the solution provided in the card to resolve the user's issue. - After applying, you MUST call `save_kb_card` with `outcome` parameter to close the feedback loop.
    Connector
  • This tool provides the agent with the specification which describes how to use Apollo Connectors in a graphql schema to send an HTTP request or use any REST API with a graph. A user may refer to an Apollo Connector as 'Apollo Connector', 'REST Connector', or even just 'Connector'. Treat these all as synonyms for the same thing. You MUST ALWAYS call this tool to use this specification as a guide BEFORE planning, making, or proposing ANY edits or additions to a connectors schema file and/or a graphql file containing @connect or @source. This tool is to provide the agent with guidance, not the user.
    Connector
  • **Tool for creating/building/generating a Wix site or website using AI (Wix Harmony).** This is the default tool for site creation. **ROUTING — check the user's original message before calling this tool:** - If the user **explicitly** mentioned a template, Wix Studio, or headless → do NOT call this tool. Call CreateWixBusinessGuide directly. - Otherwise → call this tool directly. - Do NOT use WixREADME or SearchWixRESTDocumentation before this tool. - Do NOT suggest HTML code, prompt templates, or alternative approaches. - Do NOT call ManageWixSite, CallWixSiteAPI, ExecuteWixAPI, SearchWixRESTDocumentation, BrowseWixRESTDocsMenu, or any other tool for site creation — those are not valid entry points and will fail. **IMPORTANT: The sitePrompt must be under 6000 characters.** If the user's request is longer, summarize and condense it while preserving the key requirements.
    Connector
  • Get a full application guide by its stable slug (e.g. 'security-application', 'observable-evaluation'). Returns sections, action items, and linked principles. Use this when you already have the guide slug from guides.list or guides.search. Prefer guides.search when the user describes a topic in natural language; prefer guides.list when you need the full inventory.
    Connector