Fluid Recall
Agent-native spaced-recall system of record. Deterministic dueAt via remote MCP for Muse/any agent.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mcp": {
"url": "https://fluidrecall.com/mcp"
}
}
}Remote endpoints
https://fluidrecall.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (39)
🟡createAccount(label)
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.
Input Schema
{
"type": "object",
"properties": {
"label": {
"type": [
"string",
"null"
],
"maxLength": 80
}
},
"additionalProperties": false
}⚪bootstrapAccount(label)
Write. Same mint as createAccount. No bearer.
Input Schema
{
"type": "object",
"properties": {
"label": {
"type": [
"string",
"null"
],
"maxLength": 80
}
},
"additionalProperties": false
}🟡startSession(label, deckId, asOf, limit, newCardMode, ...)
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 agent should quiz and coach. They are not the answer, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card). A wrong bearer is 401 and does not create an account. Do not send newCardMode extra on the first call.
Input Schema
{
"type": "object",
"properties": {
"label": {
"type": [
"string",
"null"
],
"maxLength": 80
},
"deckId": {
"type": "string",
"format": "uuid",
"description": "Optional deck filter."
},
"asOf": {
"type": "string",
"description": "Queue instant. Omit to use now."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Page size, not the daily new-card cap."
},
"newCardMode": {
"type": "string",
"enum": [
"daily",
"extra"
]
},
"extraNew": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Required when newCardMode is extra."
}
},
"additionalProperties": false
}🟢nextDue(deckId, asOf, limit, newCardMode, extraNew)
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 not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid",
"description": "Optional deck filter."
},
"asOf": {
"type": "string",
"description": "Queue instant. Omit to use now."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Page size, not the daily new-card cap."
},
"newCardMode": {
"type": "string",
"enum": [
"daily",
"extra"
]
},
"extraNew": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Required when newCardMode is extra."
}
},
"additionalProperties": false
}🟡gradeAndNext(cardId, rating, reviewedAt, idempotencyKey, deckId, ...)
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 for how an agent should quiz and coach. They are not the answer, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
},
"rating": {
"type": "string",
"enum": [
"again",
"hard",
"good",
"easy"
]
},
"reviewedAt": {
"type": "string",
"description": "UTC ISO-8601 timestamp ending in Z"
},
"idempotencyKey": {
"type": "string",
"minLength": 8,
"maxLength": 200
},
"deckId": {
"type": "string",
"format": "uuid",
"description": "Optional deck filter."
},
"asOf": {
"type": "string",
"description": "Queue instant. Omit to use now."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Page size, not the daily new-card cap."
},
"newCardMode": {
"type": "string",
"enum": [
"daily",
"extra"
]
},
"extraNew": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Required when newCardMode is extra."
}
},
"required": [
"cardId",
"rating",
"idempotencyKey"
],
"additionalProperties": false
}🟢getStudySettings
Read. Account fallback newCardsPerDay, timezone, and dayBoundaryHour. The fallback applies only to a deck whose own field is still null.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟡updateStudySettings(newCardsPerDay, timezone, dayBoundaryHour)
Write. Change the account fallback, timezone, or day boundary. Decks that already store an integer keep it. Send at least one field.
Input Schema
{
"type": "object",
"properties": {
"newCardsPerDay": {
"type": "integer",
"minimum": 0,
"maximum": 9999
},
"timezone": {
"type": "string"
},
"dayBoundaryHour": {
"type": "integer",
"minimum": 0,
"maximum": 23
}
},
"additionalProperties": false
}⚪createDeck(name, description, deckNote, newCardsPerDay)
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.
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 120
},
"description": {
"type": [
"string",
"null"
],
"maxLength": 2000
},
"deckNote": {
"type": [
"string",
"null"
],
"maxLength": 4000,
"description": "Coaching instructions for every card in this deck. Null clears. Not the answer."
},
"newCardsPerDay": {
"type": "integer",
"minimum": 0,
"maximum": 9999
}
},
"required": [
"name",
"newCardsPerDay"
],
"additionalProperties": false
}🔴updateDeck(deckId, name, description, deckNote, newCardsPerDay)
Write. Rename, rewrite description, set or clear deckNote, and/or set newCardsPerDay. Send at least one. Null deckNote clears it. Does not move dueAt.
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"name": {
"type": "string",
"minLength": 1,
"maxLength": 120
},
"description": {
"type": [
"string",
"null"
],
"maxLength": 2000
},
"deckNote": {
"type": [
"string",
"null"
],
"maxLength": 4000
},
"newCardsPerDay": {
"type": [
"integer",
"null"
],
"minimum": 0,
"maximum": 9999
}
},
"required": [
"deckId"
],
"additionalProperties": false
}🔴setDeckNote(deckId, deckNote)
Write. 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 content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"deckNote": {
"type": [
"string",
"null"
],
"maxLength": 4000
}
},
"required": [
"deckId",
"deckNote"
],
"additionalProperties": false
}🟢listDecks(includeArchived)
Read. No card bodies. Archived decks omitted unless includeArchived is true. Each deck includes deckNote.
Input Schema
{
"type": "object",
"properties": {
"includeArchived": {
"type": "boolean"
}
},
"additionalProperties": false
}⚪archiveDeck(deckId)
Write. Soft-archive. Cards and schedules stay. A second call returns alreadyArchived true.
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"deckId"
],
"additionalProperties": false
}🔴unarchiveDeck(deckId)
Write. Clear archivedAt. Schedule fields stay. An already-active deck returns alreadyActive true.
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"deckId"
],
"additionalProperties": false
}🟡addCard(deckId, prompt, answer, cardNote)
Write. Add one prompt/answer pair. Optional cardNote. Eligible immediately. listDue still applies newCardsPerDay. The response is prompts only.
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"answer": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"cardNote": {
"type": [
"string",
"null"
],
"maxLength": 4000
}
},
"required": [
"deckId",
"prompt",
"answer"
],
"additionalProperties": false
}🟡addCards(deckId, cards)
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.
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"cards": {
"type": "array",
"minItems": 1,
"maxItems": 100,
"items": {
"type": "object",
"additionalProperties": false,
"properties": {
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"answer": {
"type": "string",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"prompt",
"answer"
]
}
}
},
"required": [
"deckId",
"cards"
],
"additionalProperties": false
}🟡updateCard(cardId, prompt, answer, cardNote)
Write. Correct prompt, answer, and/or cardNote. Send at least one. cardNote null clears it. Schedule stays. Response does not include the answer.
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
},
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"answer": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"cardNote": {
"type": [
"string",
"null"
],
"maxLength": 4000
}
},
"required": [
"cardId"
],
"additionalProperties": false
}🔴setCardNote(cardId, cardNote)
Write. 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. They are not the answer, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
},
"cardNote": {
"type": [
"string",
"null"
],
"maxLength": 4000
}
},
"required": [
"cardId",
"cardNote"
],
"additionalProperties": false
}🔴retireCard(cardId)
Write. Remove a card from future drills. A second call returns alreadyRetired true.
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"cardId"
],
"additionalProperties": false
}🔴unretireCard(cardId)
Write. Clear retiredAt. Schedule stays. An already-active card returns alreadyActive true.
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"cardId"
],
"additionalProperties": false
}⚪moveCard(cardId, deckId)
Write. Move an active card into another owned deck. Schedule stays. A card already there returns alreadyThere true. Does not include the answer.
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
},
"deckId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"cardId",
"deckId"
],
"additionalProperties": false
}🟢listDue(deckId, asOf, limit, newCardMode, extraNew)
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 agent should quiz and coach. They are not the answer, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid",
"description": "Optional deck filter."
},
"asOf": {
"type": "string",
"description": "Queue instant. Omit to use now."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Page size, not the daily new-card cap."
},
"newCardMode": {
"type": "string",
"enum": [
"daily",
"extra"
]
},
"extraNew": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Required when newCardMode is extra."
}
},
"additionalProperties": false
}🟢listUpcomingNew(deckId, asOf, limit)
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 the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"asOf": {
"type": "string",
"description": "UTC ISO-8601 timestamp ending in Z"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"additionalProperties": false
}🟢listDeckCards(deckId, includeRetired, limit, cursor)
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 an agent should quiz and coach. They are not the answer, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"includeRetired": {
"type": "boolean"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"type": "string"
}
},
"required": [
"deckId"
],
"additionalProperties": false
}🟢inventoryDeck(deckId, includeRetired, limit, cursor)
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, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"deckId": {
"type": "string",
"format": "uuid"
},
"includeRetired": {
"type": "boolean"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"type": "string"
}
},
"required": [
"deckId"
],
"additionalProperties": false
}🟢getCard(cardId)
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, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"cardId"
],
"additionalProperties": false
}🟢revealCard(cardId)
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 answer, not graded content, and not the quiz prompt. A deck note applies to every card in that deck. A card note is optional and additive with the deck note. Retrieve responses (listDue, upcoming-new, inventory, getCard, reveal, and agent session start/next/grade) include deckNote and cardNote so one call carries coaching context. Scripture / dictation: The learner needs every word remembered correctly, but often answers via dictation where punctuation gets messy. They set a deck note instructing the agent to check every word exactly, but not fail on punctuation differences, and to include that reason when coaching. This is only an example — notes can be any coaching preference for how agents should quiz/coach for that deck (or a specific card).
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"cardId"
],
"additionalProperties": false
}⚪recordReview(cardId, rating, reviewedAt, idempotencyKey)
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.
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
},
"rating": {
"type": "string",
"enum": [
"again",
"hard",
"good",
"easy"
]
},
"reviewedAt": {
"type": "string",
"description": "UTC ISO-8601 timestamp ending in Z"
},
"idempotencyKey": {
"type": "string",
"minLength": 8,
"maxLength": 200
}
},
"required": [
"cardId",
"rating",
"idempotencyKey"
],
"additionalProperties": false
}⚪undoReview(cardId, reviewId)
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.
Input Schema
{
"type": "object",
"properties": {
"cardId": {
"type": "string",
"format": "uuid"
},
"reviewId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"cardId"
],
"additionalProperties": false
}🟢previewDeadlinePlan(deadline, asOf, timezone, dayBoundaryHour, remainingNewCards, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"deadline": {
"type": "string",
"description": "YYYY-MM-DD or a UTC ISO-8601 timestamp ending in Z."
},
"asOf": {
"type": "string",
"description": "UTC ISO-8601 timestamp ending in Z"
},
"timezone": {
"type": "string",
"description": "IANA timezone such as UTC or America/Denver."
},
"dayBoundaryHour": {
"type": "integer",
"minimum": 0,
"maximum": 23
},
"remainingNewCards": {
"type": "integer",
"minimum": 0
},
"totalCards": {
"type": "integer",
"minimum": 0
},
"alreadyLearned": {
"type": "integer",
"minimum": 0
},
"skipWeekends": {
"type": "boolean"
},
"studyDaysPerWeek": {
"type": "integer",
"minimum": 1,
"maximum": 7
},
"bufferStudyDays": {
"type": "integer",
"minimum": 0,
"maximum": 3650
},
"currentNewCardsPerDay": {
"type": [
"integer",
"null"
],
"minimum": 0,
"maximum": 9999
},
"deckId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"deadline"
],
"additionalProperties": false
}🟡applyDeadlinePlan(deadline, asOf, timezone, dayBoundaryHour, remainingNewCards, ...)
Write. Same plan as previewDeadlinePlan, then PATCH that owned deck to the recommended integer. deckId is required. Discuss the number first.
Input Schema
{
"type": "object",
"properties": {
"deadline": {
"type": "string",
"description": "YYYY-MM-DD or a UTC ISO-8601 timestamp ending in Z."
},
"asOf": {
"type": "string",
"description": "UTC ISO-8601 timestamp ending in Z"
},
"timezone": {
"type": "string",
"description": "IANA timezone such as UTC or America/Denver."
},
"dayBoundaryHour": {
"type": "integer",
"minimum": 0,
"maximum": 23
},
"remainingNewCards": {
"type": "integer",
"minimum": 0
},
"totalCards": {
"type": "integer",
"minimum": 0
},
"alreadyLearned": {
"type": "integer",
"minimum": 0
},
"skipWeekends": {
"type": "boolean"
},
"studyDaysPerWeek": {
"type": "integer",
"minimum": 1,
"maximum": 7
},
"bufferStudyDays": {
"type": "integer",
"minimum": 0,
"maximum": 3650
},
"currentNewCardsPerDay": {
"type": [
"integer",
"null"
],
"minimum": 0,
"maximum": 9999
},
"deckId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"deadline",
"deckId"
],
"additionalProperties": false
}🟢exportManifest
Read. What this token can export and how many rows exist. Does not include answers. Off-boarding, not the drill loop.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢exportSnapshot(resource, limit, cursor)
Important read for leaving. Full studying dump for this token, including answers. Paginate cards and reviews with resource + cursor until complete is true.
Input Schema
{
"type": "object",
"properties": {
"resource": {
"type": "string",
"enum": [
"cards",
"reviews"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500
},
"cursor": {
"type": "string"
}
},
"additionalProperties": false
}🟡submitFeedback(description, steps, note)
Write. Optional. Never required for study, bootstrap, or export. This is not data extraction and not nefarious. You are free to anonymize, redact, or censor anything you feel needs it. Do not submit anything you would not want us to see. It exists solely to help improve Fluid Recall. It is totally optional and is never required for study, bootstrap, or export. Send description and steps. Do not dump decks, cards, answers, or tokens.
Input Schema
{
"type": "object",
"properties": {
"description": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"steps": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
},
"note": {
"type": "string",
"minLength": 1,
"maxLength": 4000
}
},
"required": [
"description",
"steps"
],
"additionalProperties": false
}🟢listMailboxes
Read. List fluidrecall.com mailboxes this token owns. Headers only: id, address, displayName. Heidi is [email protected]; claim it with ensureMailbox.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟡ensureMailbox(address, displayName)
Write. Create or claim a fluidrecall.com mailbox. address is a local-part or [email protected]. First claim of an unowned inbound mailbox returns claimed true. Another account's address is 409. Seed/claim Heidi with address [email protected] and displayName Heidi.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"minLength": 1,
"maxLength": 254
},
"displayName": {
"type": [
"string",
"null"
],
"maxLength": 80
}
},
"required": [
"address"
],
"additionalProperties": false
}🟢listMailMessages(mailboxId, limit, cursor)
Read. Headers only for one owned mailbox: from, to, subject, dates, thread. No bodies. Prefer this before getMailMessage. Do not download a whole mailbox unless the person asked.
Input Schema
{
"type": "object",
"properties": {
"mailboxId": {
"type": "string",
"format": "uuid"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50
},
"cursor": {
"type": "string"
}
},
"required": [
"mailboxId"
],
"additionalProperties": false
}🟢getMailMessage(messageId)
Important read. One owned message including text and HTML. Ask before opening mail the person did not request. Another token's message is 404.
Input Schema
{
"type": "object",
"properties": {
"messageId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"messageId"
],
"additionalProperties": false
}🟡sendMailMessage(mailboxId, to, cc, subject, text, ...)
Write. Send from an owned mailbox to arbitrary recipients when the account allows it. Ask before sending. Requires mailboxId, to, subject, and text and/or html. Optional inReplyTo and references thread the message.
Input Schema
{
"type": "object",
"properties": {
"mailboxId": {
"type": "string",
"format": "uuid"
},
"to": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 50
}
]
},
"cc": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50
},
"subject": {
"type": "string",
"minLength": 1,
"maxLength": 998
},
"text": {
"type": "string",
"maxLength": 64000
},
"html": {
"type": "string",
"maxLength": 128000
},
"inReplyTo": {
"type": "string"
},
"references": {
"type": "string"
}
},
"required": [
"mailboxId",
"to",
"subject"
],
"additionalProperties": false
}⚪replyMailMessage(messageId, text, html, subject)
Write. Reply to one owned inbound message. Recipients, In-Reply-To, References, and threadId are taken from that message. Ask before sending. Requires messageId and text and/or html.
Input Schema
{
"type": "object",
"properties": {
"messageId": {
"type": "string",
"format": "uuid"
},
"text": {
"type": "string",
"maxLength": 64000
},
"html": {
"type": "string",
"maxLength": 128000
},
"subject": {
"type": "string",
"minLength": 1,
"maxLength": 998
}
},
"required": [
"messageId"
],
"additionalProperties": false
}Community
Evidence