Saltar al contenido
Logo de Fluid Recall

Servidor MCP de Fluid Recall

Qué servidores MCP son de Fluid Recall, del registro oficial y encontrados preguntando a su propio dominio, si responden y qué ofrecen. Un programa comprobó cada dato; nada está copiado de la página del producto.

leído el 2026-10-24

← Volver a Fluid Recall

De quién es el servidor
  • Nombre en el registrocom.fluidrecall/mcpverificado en el registro MCP

El nombre en el registro está bajo fluidrecall.com. El registro solo permite usar ese espacio de nombres a quien demuestra control del dominio por DNS o HTTP.

Cuando le preguntamoscomprobado el 2026-10-24
  • Estadorespondecomprobado el 2026-10-24
  • Herramientas34
  • El servidor se llamafluid-recall
  • Versión del servidor1.0.0
  • Versión del protocolo2025-06-18

El 2026-10-24 el servidor respondió a initialize y tools/list sin iniciar sesión. Primera respuesta en 932 ms.

¿Debe un agente conectarlo?Aún no está claro
  • Sus herramientas hacen todos los casos de uso comprobados: Store flashcard decks and cards for later recall; Get the next due time after each rating; Coach a recall session in chat before revealing answers.
  • Comprobado 4 de los 7 días necesarios para juzgar su fiabilidad.

Una vez conectado

  • Para "Get the next due time after each rating", la primera llamada probable es gradeAndNext.
  • Para "Coach a recall session in chat before revealing answers", la primera llamada probable es startSession.
  • createAccount, updateStudySettings, createDeck, updateDeck, setDeckNote cambian datos sin iniciar sesión: cualquiera con la dirección puede llamarlas.
  • Parámetros sin tipo o sin descripción en 31 de 34 herramientas: revisa los argumentos antes de llamar.

Lo dicen reglas a partir de las mediciones de arriba. La primera llamada probable la elige un modelo de la lista de herramientas; lee su descripción antes de fiarte.

Medido cada díacomprobaciones diarias: 4, la primera el 2026-10-24
  • Nota INITE MCPtras una semanala nota necesita 7 comprobaciones diarias: 4 hasta ahora
  • Qué puede hacer un agente con él3 de 3 casos de uso
  • Respondiómidiendo4 de las 7 comprobaciones diarias necesarias para mostrar el porcentaje
  • Mediana de la primera respuesta947 ms
  • Espacio en el contexto del agente≈ 6567 tokenslas definiciones de todas sus herramientas (34), que el agente lleva en cada turno
  • Definiciones de herramientasB · 85 de 100
  • Resultados tipados0 de 34 herramientasdeclaran outputSchema: el resultado llega tipado y se lee de una vez
  • Parámetros sin descripción: en 31 de 34

Qué puede hacer un agente con él

  • puede · Store flashcard decks and cards for later recall
  • puede · Get the next due time after each rating
  • puede · Coach a recall session in chat before revealing answers

Cada caso de uso del producto se le preguntó a Jev junto con la lista de herramientas de este servidor: ¿puede un agente hacerlo con estas herramientas?

Conviene revisar

  • Herramientas que cambian datos, en un servidor que responde sin iniciar sesión: createAccount, updateStudySettings, createDeck, updateDeck, setDeckNote

Un programa comprueba el servidor una vez al día: initialize y tools/list, sin modelo. Los tokens son la longitud de las definiciones, a unos cuatro caracteres por token. La nota promedia seis comprobaciones del nombre, la descripción, el esquema y las anotaciones de cada herramienta; dice lo bien descritas que están, no si funcionan. La nota pondera solo lo medido: si responde (25%), si hace el trabajo del producto (25%), definiciones (20%), contexto (10%), uso (10%) y lo fácil que es conectarse (10%). Lo que no se midió queda fuera, y una instrucción oculta limita la nota a 40. El estado de los servidores MCP de los proveedores: método y números →

Herramientas que ofrece34 herramientas · leído el 2026-10-24
  • createAccount

    Write. No bearer. Mint an anonymous account and a personal API token. Save the token for later Authorization: Bearer calls. The token is the tenant. Do not send a userId.

  • bootstrapAccount

    Write. Same mint as createAccount. No bearer.

  • startSession

    Write when no bearer (mints a token), read when a bearer is present. Returns the account (when minted), the due queue, and first. Prompts only. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an…

  • nextDue

    Read. Due queue and first prompt. Requires a bearer. Prompts only. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an agent should quiz and coach. They are not the answer, not graded content, and…

  • gradeAndNext

    Write. recordReview, then the next due prompt. Requires cardId, rating, reviewedAt optional, and a new idempotencyKey. Schedule from dueAt. Prompts only. Includes deckNote and cardNote (null when unset). Coaching notes are instructions…

  • getStudySettings

    Read. Account fallback newCardsPerDay, timezone, and dayBoundaryHour. The fallback applies only to a deck whose own field is still null.

  • get_profile

    Read. OpenAI profile for connection linking. Stable profile id (id), the account label when set (name), and optional email/nickname. No decks, cards, answers, or tokens. Requires a bearer or OAuth token.

  • updateStudySettings

    Write, destructive. Change the account fallback, timezone, or day boundary. Decks that already store an integer keep it. Send at least one field.

  • createDeck

    Write. name and newCardsPerDay are required. Choose that integer with the person; there is no default of 20. Optional description and deckNote. Setting a note does not move dueAt.

  • updateDeck

    Write, destructive. Rename, rewrite description, set or clear deckNote, and/or set newCardsPerDay. Send at least one. Null deckNote clears it. Does not move dueAt.

  • setDeckNote

    Write, destructive. Set or clear a deck coaching note. deckNote null clears it. Same write as updateDeck. Does not move dueAt. Coaching notes are instructions for how an agent should quiz and coach. They are not the answer, not graded…

  • listDecks

    Read. No card bodies. Archived decks omitted unless includeArchived is true. Each deck includes deckNote.

  • archiveDeck

    Write, destructive. Soft-archive a deck; it leaves listDue and the default deck list until unarchiveDeck. Cards and schedules stay. A second call returns alreadyArchived true.

  • unarchiveDeck

    Write. Clear archivedAt. Schedule fields stay. An already-active deck returns alreadyActive true.

  • addCard

    Write. Add one prompt/answer pair. Optional cardNote. Eligible immediately. listDue still applies newCardsPerDay. The response is prompts only.

  • addCards

    Write. Add 1 to 100 prompt/answer pairs to one owned deck. All or nothing. Prompts only. After this, re-run previewDeadlinePlan with that deckId.

  • updateCard

    Write, destructive. Correct prompt, answer, and/or cardNote. Send at least one. cardNote null clears it. Schedule stays. Response does not include the answer.

  • setCardNote

    Write, destructive. Set or clear a card coaching note. cardNote null clears it. Additive with the deck note. Same write as updateCard. Does not include the answer. Coaching notes are instructions for how an agent should quiz and coach…

  • retireCard

    Write, destructive. Remove a card from future drills; reversible only with unretireCard. A second call returns alreadyRetired true. Inventory the deck first when the cardId is not in the due list.

  • unretireCard

    Write. Clear retiredAt. Schedule stays. An already-active card returns alreadyActive true.

  • moveCard

    Write. Move an active card into another owned deck. Schedule stays. A card already there returns alreadyThere true. Does not include the answer.

  • listDue

    Read. Prompts only. answerIncluded is false. Ordered learning, then review, then new. The new queue is capped by each deck's newCardsPerDay. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an…

  • listUpcomingNew

    Read. New cards the daily cap is holding back. Prompts only. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an agent should quiz and coach. They are not the answer, not graded content, and not…

  • listDeckCards

    Read. Prompt-only inventory of one owned deck, including cards that are not due. Order is dueAt, then createdAt, then cardId — not the drill order. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how…

  • inventoryDeck

    Read. Same as listDeckCards. Use this when you need a cardId that is not in the due list. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an agent should quiz and coach. They are not the answer…

  • getCard

    Read. One card's prompt and schedule. No answer. A retired card is 404. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an agent should quiz and coach. They are not the answer, not graded content…

  • revealCard

    Important read. One answer, after the person has tried to recall. Do not fold this into listDue. Includes deckNote and cardNote (null when unset). Coaching notes are instructions for how an agent should quiz and coach. They are not the…

  • recordReview

    Write. Rating again | hard | good | easy plus reviewedAt and a new idempotencyKey. The scheduler returns dueAt. Do not invent an interval. Same key and body returns the original result.

  • undoReview

    Write. Undo the latest active grade, or reviewId when it is that latest one. Restores dueAt. A second undo of the same review returns alreadyUndone true. Does not include the answer.

  • previewDeadlinePlan

    Read. Recommend newCardsPerDay from a deadline: ceil(remaining new cards / study days). Does not write. Send remainingNewCards, totalCards, or deckId. There is no silent default of 20.

  • applyDeadlinePlan

    Write, destructive. Same plan as previewDeadlinePlan, then PATCH that owned deck to the recommended integer. deckId is required. Discuss the number first.

  • exportManifest

    Read. What this token can export and how many rows exist. Does not include answers. Off-boarding, not the drill loop.

  • exportSnapshot

    Important read for leaving. Full studying dump for this token, including answers. Paginate cards and reviews with resource + cursor until complete is true.

  • submitFeedback

    Write. Optional. Never required for study, bootstrap, or export. Append-only: feedback is logged and never edits study data. This is not data extraction and not nefarious. You are free to anonymize, redact, or censor anything you feel…

Cómo conectar

Añade el servidor a la configuración de tu cliente MCP. Claude Desktop, Cursor y la mayoría de los demás clientes leen este formato:

{
  "mcpServers": {
    "fluidrecall": {
      "type": "http",
      "url": "https://fluidrecall.com/mcp"
    }
  }
}

Añadirlo

Claude Code, en una terminal

claude mcp add --transport http fluidrecall https://fluidrecall.com/mcp

Añadir a CursorAñadir a VS Code

claude.ai, ChatGPT y otros clientes: añade https://fluidrecall.com/mcp como conector personalizado en los ajustes.

Especificación OpenAPI

85 rutas, leído el 2026-10-24. Abrir la especificación ↗

Cada línea es algo que un programa encontró al buscar: la entrada del registro, la respuesta del propio servidor, una especificación que se puede leer. Si falta una línea, es que no la encontramos, no que no exista.