Nutcracker is an MCP server published by com.heynutcracker, hosted at heynutcracker.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 34 tools, including list_spaces, create_space, merge_space, start_task, get_task.
Creative work for brand teams: strategy, copy, ideas, research, decks, key visuals and video ads.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Spaces in the connected workspace this user can open, most recently active first. path shows nesting ("Kova / Winter launch"): a sub-space also reads its parents' pinned docs and elements. scope says who sees the work: team is everyone in the workspace, personal is your human alone. Pass query to find one by name.
| Parameter | Type | Description |
|---|---|---|
| query | string | Words to find in the path; any word matches, most words first. |
| cursor | string | next_cursor from the previous page. |
{
"name": "list_spaces",
"title": "List spaces",
"description": "Spaces in the connected workspace this user can open, most recently active first. path shows nesting (\"Kova / Winter launch\"): a sub-space also reads its parents' pinned docs and elements. scope says who sees the work: team is everyone in the workspace, personal is your human alone. Pass query to find one by name.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"query": {
"type": "string",
"description": "Words to find in the path; any word matches, most words first."
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous page."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Make a space when list_spaces has none that fits. If this place already has a space with the name, that one comes back with created: false instead of a second. If a space with a similar name exists anywhere, nothing is made and only those come back, as similar: use the one that is the same project, or call again with create_anyway: true when none is. A sub-space (parent_id) also reads its parent's pinned docs and elements, and takes its parent's scope. Otherwise scope decides who sees it: personal, the default, is your human alone; team is everyone in the workspace, so make a team space only when your human agrees.
| Parameter | Type | Description |
|---|---|---|
| name * | string | |
| scope | string | Who sees a top-level space. Default personal. |
| parent_id | string | A space id from list_spaces, to make a sub-space of it. |
| create_anyway | boolean | Make it even though similar names came back. |
{
"name": "create_space",
"title": "Create space",
"description": "Make a space when list_spaces has none that fits. If this place already has a space with the name, that one comes back with created: false instead of a second. If a space with a similar name exists anywhere, nothing is made and only those come back, as similar: use the one that is the same project, or call again with create_anyway: true when none is. A sub-space (parent_id) also reads its parent's pinned docs and elements, and takes its parent's scope. Otherwise scope decides who sees it: personal, the default, is your human alone; team is everyone in the workspace, so make a team space only when your human agrees.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"scope": {
"enum": [
"personal",
"team"
],
"type": "string",
"description": "Who sees a top-level space. Default personal."
},
"parent_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces, to make a sub-space of it."
},
"create_anyway": {
"type": "boolean",
"description": "Make it even though similar names came back."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Fold a duplicate space into another: its chats, docs, rolls, files, pins, collections, sub-spaces and memory move into into_id, and the emptied space goes to Trash. Both must sit under the same Personal or Team. This is refused until your human agrees: ask them, then call again with agreed: true. Only who made the space, or a workspace admin, can merge it. files_already_there in the result names the files into_id already held, as into_id names them: the merged space's copies went to Trash, and these serve every pin and chat that used them.
| Parameter | Type | Description |
|---|---|---|
| agreed | boolean | true only once your human agreed to the merge the refusal named. |
| into_id * | string | The space that keeps everything. |
| space_id * | string | The duplicate that goes to Trash. |
{
"name": "merge_space",
"title": "Merge space",
"description": "Fold a duplicate space into another: its chats, docs, rolls, files, pins, collections, sub-spaces and memory move into into_id, and the emptied space goes to Trash. Both must sit under the same Personal or Team. This is refused until your human agrees: ask them, then call again with agreed: true. Only who made the space, or a workspace admin, can merge it. files_already_there in the result names the files into_id already held, as into_id names them: the merged space's copies went to Trash, and these serve every pin and chat that used them.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id",
"into_id"
],
"properties": {
"agreed": {
"type": "boolean",
"description": "true only once your human agreed to the merge the refusal named."
},
"into_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "The space that keeps everything."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "The duplicate that goes to Trash."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Start a creative task (writing, strategy, naming, ideas, research-backed docs) as a new Nutcracker chat in a space; what Nutcracker knows about the brand, the memory of the space and its pins apply. Returns task_id and the chat url. A task takes minutes: poll get_task until it is no longer running.
| Parameter | Type | Description |
|---|---|---|
| brief * | string | What to make and who it is for, in plain words, as your human or their client would say it. |
| files | array | file_id values from sending files to upload_file urls. |
| model | string | A name from list_models with kind writer and chat true, only when your human named one ("run it on Opus"). Without it the task runs on the workspace default, which suits most work. |
| memory | string | What the task does with memory, as the chat's own setting. normal: Uses memory and adds what it learns. In a team space, it helps the team’s chats. dont-add: Uses memory. Nothing from this chat is kept for later or for the team. no-memory: Doesn’t use or add to memory. Works only from what you give … |
| context | string | What is known: facts, numbers, sources, what the client said and hard limits. Not your reading of them, and no test of your own for a good answer. |
| doc_ids | array | Docs, presentations or storyboards the task must read (ids from get_task, list_space or create_doc). |
| space_id * | string | A space id from list_spaces. |
Where a task stands: running, needs_input (answer the question with reply), done, or failed. While running, progress names the step in flight (research, skill, ...; null while it thinks or writes the reply), its latest headline, and how many sources research has read. Returns the answer the latest reply ends with (a failed task: all it wrote) with evidence as links and [image card: name] where a card stands, the space the task is in now (null outside any space; a chat can move), the sources it cites, the skills it used, the brand it was for, the other AI behind a take, steers_taken (messages sent while it ran that the reply took), the documents the task made (id, title, url), its images, video and sound with file urls and the credits each spent, and the image and video cards of the latest reply with their price (made: true when the card already has its picture or clip, so generate would buy another take): run one with generate once your human agrees to the price. memory_suggestions lists lines waiting for your human's yes before the space's memory keeps them; ask them, then answer with answer_memory.
| Parameter | Type | Description |
|---|---|---|
| seen | string | The seen value from your last get_task: leaves out the reply, sources and cards you already read, and media that has not changed. Leave it out to read the cards and their prices again. |
| task_id * | string | A task_id, or a chat id from list_space. |
| all_sources | boolean | List every source the task saw (sources_seen counts them), not only those the reply cites. |
| wait_seconds | number | Hold the call while the task, or once it is done its media, is still going, up to 45 seconds; it returns as soon as that ends. Use it instead of polling fast. |
Save or dismiss lines from get_task memory_suggestions, as your human answered. Saved lines join the space's memory and reach every chat in it; a dismissed line is not suggested again in that space. Returns each line's state; one answered in the app already keeps that answer.
| Parameter | Type | Description |
|---|---|---|
| save | array | memory_suggestions ids your human said to keep. |
| dismiss | array | memory_suggestions ids your human said no to. |
| task_id * | string |
{
"name": "answer_memory",
"title": "Answer memory suggestions",
"description": "Save or dismiss lines from get_task memory_suggestions, as your human answered. Saved lines join the space's memory and reach every chat in it; a dismissed line is not suggested again in that space. Returns each line's state; one answered in the app already keeps that answer.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id"
],
"properties": {
"save": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"maxItems": 50,
"description": "memory_suggestions ids your human said to keep."
},
"dismiss": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"maxItems": 50,
"description": "memory_suggestions ids your human said no to."
},
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Run one image or video card from get_task: this spends the workspace credits, so ask your human first, naming the card and its price. Refused when the price is no longer accept_price or the card now leaves out other images; read get_task again without seen then. The result lands in the task roll; poll get_task for files.
| Parameter | Type | Description |
|---|---|---|
| card * | string | A card id from get_task cards. |
| task_id * | string | |
| left_out | array | The card's left_out image ids, as get_task listed them. |
| accept_price * | any | The card price your human agreed to; null when get_task shows no price (set when it runs). |
{
"name": "generate",
"title": "Generate media",
"description": "Run one image or video card from get_task: this spends the workspace credits, so ask your human first, naming the card and its price. Refused when the price is no longer accept_price or the card now leaves out other images; read get_task again without seen then. The result lands in the task roll; poll get_task for files.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id",
"card",
"accept_price"
],
"properties": {
"card": {
"type": "string",
"description": "A card id from get_task cards."
},
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"left_out": {
"type": "array",
"items": {
"type": "string"
},
"description": "The card's left_out image ids, as get_task listed them."
},
"accept_price": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0
},
{
"type": "null"
}
],
"description": "The card price your human agreed to; null when get_task shows no price (set when it runs)."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Send the next message in a task: answer its question (an option or your own words) or ask for a revision. While the task runs, a message alone (no docs or files) reaches it at its next step: use that for what your human adds or corrects mid-task, not for status or a restated brief. Or, in place of a message, pass another_ai for another model to write its own version of the latest reply, kept beside it in the app. Returns the same task_id; poll get_task again.
| Parameter | Type | Description |
|---|---|---|
| files | array | file_id values from sending files to upload_file urls. |
| doc_ids | array | Docs, presentations or storyboards the task must read (ids from get_task, list_space or create_doc). |
| message | string | Required unless another_ai is set. |
| task_id * | string | |
| another_ai | any | true for the next lab this task has not heard from, or a name from list_models with kind writer, only when your human named one ("GPT"). Works on a reply made with a skill. |
{
"name": "reply",
"title": "Reply to task",
"description": "Send the next message in a task: answer its question (an option or your own words) or ask for a revision. While the task runs, a message alone (no docs or files) reaches it at its next step: use that for what your human adds or corrects mid-task, not for status or a restated brief. Or, in place of a message, pass another_ai for another model to write its own version of the latest reply, kept beside it in the app. Returns the same task_id; poll get_task again.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id"
],
"properties": {
"files": {
"type": "array",
"items": {
"type": "string",
"pattern": "^(media|doc):[0-9a-f-]{36}$|^clip:[\\w-]+\\.[\\w-]+$"
},
"maxItems": 16,
"description": "file_id values from sending files to upload_file urls."
},
"doc_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"maxItems": 10,
"description": "Docs, presentations or storyboards the task must read (ids from get_task, list_space or create_doc)."
},
"message": {
"type": "string",
"minLength": 1,
"description": "Required unless another_ai is set."
},
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"another_ai": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "string",
"minLength": 1
}
],
"description": "true for the next lab this task has not heard from, or a name from list_models with kind writer, only when your human named one (\"GPT\"). Works on a reply made with a skill."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}The models this user can use. image, video and sound: house default first, with sizes, ratios, lengths and what each takes. A task uses the default unless the brief or reply names one; prices show on the cards get_task returns. writer: the models reply's another_ai can name; start_task's model takes only those with chat true.
| Parameter | Type | Description |
|---|---|---|
| kind * | string | one of ["image","video","sound","writer"] |
{
"name": "list_models",
"title": "List models",
"description": "The models this user can use. image, video and sound: house default first, with sizes, ratios, lengths and what each takes. A task uses the default unless the brief or reply names one; prices show on the cards get_task returns. writer: the models reply's another_ai can name; start_task's model takes only those with chat true.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"kind"
],
"properties": {
"kind": {
"enum": [
"image",
"video",
"sound",
"writer"
],
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}The kinds of work Nutcracker knows, each with what it returns (gives), the shapes it starts from (takes) and the shape it hands on (makes). Shapes run brief, evidence, insight, strategy, idea, platform, execution; review judges finished work. Name one in the brief when it fits ("run a Brand Scan"); otherwise describe the outcome and Nutcracker picks.
No parameters.
{
"name": "list_work",
"title": "List kinds of work",
"description": "The kinds of work Nutcracker knows, each with what it returns (gives), the shapes it starts from (takes) and the shape it hands on (makes). Shapes run brief, evidence, insight, strategy, idea, platform, execution; review judges finished work. Name one in the brief when it fits (\"run a Brand Scan\"); otherwise describe the outcome and Nutcracker picks.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Get a link to send one image, video or document from your disk (logo, screenshot, product shot, PDF) for a task to work from. Send the file with an HTTP PUT, e.g. curl -T <path> '<upload_url>'; the answer is JSON with the file_id to pass in files on start_task or reply. The link works for 15 minutes. One file_id works for any number of tasks. A document up to 100 MB, an image up to 20 MB. A video (up to 1 GB) or sound (up to 200 MB) needs size_bytes, its exact size: the answer gives its file_id (or media_id) at once, and the PUT must carry the headers it names, e.g. curl -T <path> -H 'Content-Type: video/mp4' '<upload_url>'. Upload an image or video right before the task that uses it: about 20 can wait unsent, and waiting ones also block your human uploading in the app. A large scan can take minutes to read; start_task says when it is not ready yet. With space_id, a document joins that space's Files instead: every chat in the space reads it, the team sees it, and pin can make it required reading. The answer comes once it is read, with its space_file_id; no file_id is needed for tasks there. A long read answers reading: true, and list_space shows the file when it is done. A PNG, JPEG, WebP, GIF or SVG image with space_id goes to that space and answers its image_id: add_images sorts it into the space's collections, pin makes it material every chat reads, and create_element makes it an @element. An MP4, MOV or WebM video or an MP3, WAV or M4A sound with space_id answers a media_id for create_element. An upload nothing holds is deleted after a day.
| Parameter | Type | Description |
|---|---|---|
| filename * | string | Its name with extension, which sets how it is read. |
| space_id | string | A space id from list_spaces, to keep a document in its Files or an image in its images rather than give it to one task. |
| size_bytes | integer | A video or sound: its exact size in bytes (wc -c < file), which the storage link is signed for. |
The workspace's credits left, before you plan or agree to media spend. unlimited means no credits limit spending and prices are for reference, since nothing is deducted; still ask your human before generate. blocked says why it can spend nothing now, and fix who can add more.
No parameters.
{
"name": "get_credits",
"title": "Get credits",
"description": "The workspace's credits left, before you plan or agree to media spend. unlimited means no credits limit spending and prices are for reference, since nothing is deducted; still ask your human before generate. blocked says why it can spend nothing now, and fix who can add more.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Read one roll of images, video and sound, newest first: on the first page its reference shelf (references, the pictures, clips and sounds put beside it, up to 60, references_more counts the rest; in_prompt marks those on its prompt now), then each generation with its status, file urls and prompt (long ones end in …, a repeat reads "Same prompt as above."), and the roll's own @elements; list_elements has the space's. Pass query to find "the one where…" by words in its prompt, cursor to read on, or generation_ids for those generations with full prompts. Roll ids come from list_space or a storyboard. A file marked favorite is one your human hearted in the app, their pick from the roll; favorites=true lists only generations with one.
| Parameter | Type | Description |
|---|---|---|
| query | string | Words to find in prompts; any word matches, most words first. |
| cursor | string | next_cursor from the previous page. |
| roll_id * | string | |
| favorites | boolean | Only generations with a file your human hearted. |
| generation_ids | array | Only these generations, with full prompts. |
{
"name": "read_roll",
"title": "Read roll",
"description": "Read one roll of images, video and sound, newest first: on the first page its reference shelf (references, the pictures, clips and sounds put beside it, up to 60, references_more counts the rest; in_prompt marks those on its prompt now), then each generation with its status, file urls and prompt (long ones end in …, a repeat reads \"Same prompt as above.\"), and the roll's own @elements; list_elements has the space's. Pass query to find \"the one where…\" by words in its prompt, cursor to read on, or generation_ids for those generations with full prompts. Roll ids come from list_space or a storyboard. A file marked favorite is one your human hearted in the app, their pick from the roll; favorites=true lists only generations with one.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"roll_id"
],
"properties": {
"query": {
"type": "string",
"description": "Words to find in prompts; any word matches, most words first."
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous page."
},
"roll_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"favorites": {
"type": "boolean",
"description": "Only generations with a file your human hearted."
},
"generation_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"description": "Only these generations, with full prompts."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}The @elements of a space (a character, product, place or voice with its reference media), including those it inherits from parent spaces: each element_id, name, description and media (media_id, kind, url, and seconds for video and audio). An inherited one names the space it comes from; change it there. Elements of a single roll are in read_roll.
| Parameter | Type | Description |
|---|---|---|
| space_id * | string | A space id from list_spaces. |
{
"name": "list_elements",
"title": "List elements",
"description": "The @elements of a space (a character, product, place or voice with its reference media), including those it inherits from parent spaces: each element_id, name, description and media (media_id, kind, url, and seconds for video and audio). An inherited one names the space it comes from; change it there. Elements of a single roll are in read_roll.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id"
],
"properties": {
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Make an @element in a space from images, a video or a voice you sent there, so every image and video made in the space and its sub-spaces keeps that character, product or place the same when a prompt names @name. Send each file with upload_file and space_id first. The answer has the element_id.
| Parameter | Type | Description |
|---|---|---|
| name * | string | What a prompt calls it after @: letters, digits and _, with a letter, up to 30. |
| space_id * | string | A space id from list_spaces. |
| media_ids * | array | media_id values from upload_file's answers with space_id, or from list_elements: up to 4 images (the first is the face) or one video instead, plus one voice or sound. A video runs at least 3 s and audio at least 5 s; a model uses the first seconds it takes of a longer one. |
| description | string | Who or what it is, in a line a prompt can lean on. |
{
"name": "create_element",
"title": "Create element",
"description": "Make an @element in a space from images, a video or a voice you sent there, so every image and video made in the space and its sub-spaces keeps that character, product or place the same when a prompt names @name. Send each file with upload_file and space_id first. The answer has the element_id.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id",
"name",
"media_ids"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9_]*[A-Za-z_][A-Za-z0-9_]*$",
"maxLength": 30,
"description": "What a prompt calls it after @: letters, digits and _, with a letter, up to 30."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
},
"media_ids": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
{
"type": "string",
"pattern": "^clip:[\\w-]+\\.[\\w-]+$"
}
]
},
"maxItems": 6,
"minItems": 1,
"description": "media_id values from upload_file's answers with space_id, or from list_elements: up to 4 images (the first is the face) or one video instead, plus one voice or sound. A video runs at least 3 s and audio at least 5 s; a model uses the first seconds it takes of a longer one."
},
"description": {
"type": "string",
"maxLength": 500,
"description": "Who or what it is, in a line a prompt can lean on."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Change one of a space's own @elements: its name, description or media. media_ids replaces the whole set, so pass the ones to keep (from list_elements) with the new ones; one it already holds keeps the trim set in the app. Change an inherited element in the space it comes from.
| Parameter | Type | Description |
|---|---|---|
| name | string | What a prompt calls it after @: letters, digits and _, with a letter, up to 30. |
| space_id * | string | A space id from list_spaces. |
| media_ids | array | media_id values from upload_file's answers with space_id, or from list_elements: up to 4 images (the first is the face) or one video instead, plus one voice or sound. A video runs at least 3 s and audio at least 5 s; a model uses the first seconds it takes of a longer one. |
| element_id * | string | An element_id from list_elements. |
| description | string | Who or what it is, in a line a prompt can lean on. |
{
"name": "update_element",
"title": "Update element",
"description": "Change one of a space's own @elements: its name, description or media. media_ids replaces the whole set, so pass the ones to keep (from list_elements) with the new ones; one it already holds keeps the trim set in the app. Change an inherited element in the space it comes from.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id",
"element_id"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9_]*[A-Za-z_][A-Za-z0-9_]*$",
"maxLength": 30,
"description": "What a prompt calls it after @: letters, digits and _, with a letter, up to 30."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
},
"media_ids": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
{
"type": "string",
"pattern": "^clip:[\\w-]+\\.[\\w-]+$"
}
]
},
"maxItems": 6,
"minItems": 1,
"description": "media_id values from upload_file's answers with space_id, or from list_elements: up to 4 images (the first is the face) or one video instead, plus one voice or sound. A video runs at least 3 s and audio at least 5 s; a model uses the first seconds it takes of a longer one."
},
"element_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "An element_id from list_elements."
},
"description": {
"type": "string",
"maxLength": 500,
"description": "Who or what it is, in a line a prompt can lean on."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Move a chat, roll, space, collection or space file into another space (a doc moves with update_doc_info). A sub-space moves with everything in it; a space can also go to the top of Personal or Team with to_top_level. Collections and files stay under their own Personal or Team. A move that changes who can open something (a roll or space going between Personal and Team, guests gaining or losing a space, a chat's roll following it) is refused until your human agrees: ask them, then call again with agreed: true.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Its id from list_space (space_file_id for a file, collection_id for a collection). |
| kind * | string | one of ["chat","roll","space","collection","file"] |
| agreed | boolean | true only once your human agreed to what the refusal named. |
| to_space_id | string | A space id from list_spaces. |
| to_top_level | string | A space only, instead of to_space_id. |
| from_space_id | string | A file only: the space it is in now. |
{
"name": "move",
"title": "Move",
"description": "Move a chat, roll, space, collection or space file into another space (a doc moves with update_doc_info). A sub-space moves with everything in it; a space can also go to the top of Personal or Team with to_top_level. Collections and files stay under their own Personal or Team. A move that changes who can open something (a roll or space going between Personal and Team, guests gaining or losing a space, a chat's roll following it) is refused until your human agrees: ask them, then call again with agreed: true.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"kind",
"id"
],
"properties": {
"id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "Its id from list_space (space_file_id for a file, collection_id for a collection)."
},
"kind": {
"enum": [
"chat",
"roll",
"space",
"collection",
"file"
],
"type": "string"
},
"agreed": {
"type": "boolean",
"description": "true only once your human agreed to what the refusal named."
},
"to_space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
},
"to_top_level": {
"enum": [
"personal",
"team"
],
"type": "string",
"description": "A space only, instead of to_space_id."
},
"from_space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A file only: the space it is in now."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Rename a space, chat, roll, collection, or a picture, clip or sound in a space's Files (kind media, with space_id). A doc renames with update_doc_info; an uploaded document keeps its name. Everyone who can open it sees the new name.
| Parameter | Type | Description |
|---|---|---|
| id * | string | Its id from list_spaces or list_space (collection_id for a collection, media_id for media). |
| kind * | string | one of ["space","chat","roll","collection","media"] |
| name * | string | |
| space_id | string | Media only: the space whose Files hold it. |
{
"name": "rename",
"title": "Rename",
"description": "Rename a space, chat, roll, collection, or a picture, clip or sound in a space's Files (kind media, with space_id). A doc renames with update_doc_info; an uploaded document keeps its name. Everyone who can open it sees the new name.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"kind",
"id",
"name"
],
"properties": {
"id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "Its id from list_spaces or list_space (collection_id for a collection, media_id for media)."
},
"kind": {
"enum": [
"space",
"chat",
"roll",
"collection",
"media"
],
"type": "string"
},
"name": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "Media only: the space whose Files hold it."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Remove a file from a space's Files to Trash and off its pins; restoring it in the app within 30 days pins it again. A picture, clip or sound (media_id) is refused while the space collects it, names it as an @element or has it on a roll prompt, and the refusal says where.
| Parameter | Type | Description |
|---|---|---|
| media_id | string | Instead: a picture, clip or sound from list_space media. |
| space_id * | string | The space whose Files hold it. |
| space_file_id | string | An uploaded document from list_space files. |
{
"name": "delete_file",
"title": "Delete file",
"description": "Remove a file from a space's Files to Trash and off its pins; restoring it in the app within 30 days pins it again. A picture, clip or sound (media_id) is refused while the space collects it, names it as an @element or has it on a roll prompt, and the refusal says where.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id"
],
"properties": {
"media_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "Instead: a picture, clip or sound from list_space media."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "The space whose Files hold it."
},
"space_file_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "An uploaded document from list_space files."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Send a space to Trash with everything in it: sub-spaces, chats, docs, rolls, files, pins and collections. It can be restored from Trash in the app for 30 days. This is refused until your human agrees: ask them, then call again with agreed: true. Only who made the space, or a workspace admin, can delete it. To keep the work, merge_space or move it first.
| Parameter | Type | Description |
|---|---|---|
| agreed | boolean | true only once your human agreed to the delete the refusal named. |
| space_id * | string | A space id from list_spaces. |
{
"name": "delete_space",
"title": "Delete space",
"description": "Send a space to Trash with everything in it: sub-spaces, chats, docs, rolls, files, pins and collections. It can be restored from Trash in the app for 30 days. This is refused until your human agrees: ask them, then call again with agreed: true. Only who made the space, or a workspace admin, can delete it. To keep the work, merge_space or move it first.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id"
],
"properties": {
"agreed": {
"type": "boolean",
"description": "true only once your human agreed to the delete the refusal named."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Read a doc, presentation or storyboard as it is now, including edits the team made in the app. A doc comes back as Markdown and a presentation as its JSON. A storyboard comes back as its script: treatment, cast, each film's shots with seconds, action and lines, and a link to each picked frame. An <evidence_card/> marker is an exhibit the doc shows (about and url say what it is): keep or move its markers when you rewrite the text, edit its caption there, and leave them out to drop it. Copied into another doc with create_doc or update_doc, a marker brings its exhibit along.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | A doc id from get_task or list_space. |
| prompts | boolean | A storyboard only: also return each shot's frame prompt. |
{
"name": "read_doc",
"title": "Read doc",
"description": "Read a doc, presentation or storyboard as it is now, including edits the team made in the app. A doc comes back as Markdown and a presentation as its JSON. A storyboard comes back as its script: treatment, cast, each film's shots with seconds, action and lines, and a link to each picked frame. An <evidence_card/> marker is an exhibit the doc shows (about and url say what it is): keep or move its markers when you rewrite the text, edit its caption there, and leave them out to drop it. Copied into another doc with create_doc or update_doc, a marker brings its exhibit along.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
},
"prompts": {
"type": "boolean",
"description": "A storyboard only: also return each shot's frame prompt."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Publish a doc, presentation or storyboard: returns its public read-only link, which anyone with the link can open without an account. Returns the existing link when there is one. The link shows in the doc Share panel.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | A doc id from get_task or list_space. |
{
"name": "share_link",
"title": "Share link",
"description": "Publish a doc, presentation or storyboard: returns its public read-only link, which anyone with the link can open without an account. Returns the existing link when there is one. The link shows in the doc Share panel.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}Turn off the public link of a doc, presentation or storyboard. Anyone opening the old link gets nothing; a copy someone already saved stays with them.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | A doc id from get_task or list_space. |
{
"name": "unshare",
"title": "Turn off link",
"description": "Turn off the public link of a doc, presentation or storyboard. Anyone opening the old link gets nothing; a copy someone already saved stays with them.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}A file of a doc, presentation or storyboard to download and attach: pdf or docx for a doc, pptx or pdf for a presentation, the frames as a zip for a storyboard (full size; zip_small to attach to a mail). To see how a presentation is drawn, read its pdf, or one slide as png with slide_id. Returns a download url that works for 15 minutes; the file is made when the url is fetched, which can take up to a minute for a presentation. An X-Missing-Pictures response header counts pictures that could not be reached and were left out.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | A doc id from get_task or list_space. |
| format | string | Leave out for the usual file of its type. |
| slide_id | string | One slide of a presentation, as a png: an id from its slides in read_doc. |
{
"name": "export",
"title": "Export",
"description": "A file of a doc, presentation or storyboard to download and attach: pdf or docx for a doc, pptx or pdf for a presentation, the frames as a zip for a storyboard (full size; zip_small to attach to a mail). To see how a presentation is drawn, read its pdf, or one slide as png with slide_id. Returns a download url that works for 15 minutes; the file is made when the url is fetched, which can take up to a minute for a presentation. An X-Missing-Pictures response header counts pictures that could not be reached and were left out.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
},
"format": {
"enum": [
"pdf",
"docx",
"pptx",
"zip",
"zip_small",
"png"
],
"type": "string",
"description": "Leave out for the usual file of its type."
},
"slide_id": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "One slide of a presentation, as a png: an id from its slides in read_doc."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Everything in one space: docs (type doc, deck for a presentation, or storyboard), chats and rolls of images and video, newest first, with app links and whether a doc has a public link. Pass cursor to read on. pins lists what every chat here reads, parent spaces included; files lists the space's Files, the documents every chat here can read; media lists the pictures, clips and sounds people brought into the space on purpose, newest 60 (media_more counts the rest; a picture's media_id is its image_id). collections lists how the space's images are sorted, with the groups in each, parent spaces included.
| Parameter | Type | Description |
|---|---|---|
| cursor | string | next_cursor from the previous page. |
| space_id * | string | A space id from list_spaces. |
{
"name": "list_space",
"title": "List space",
"description": "Everything in one space: docs (type doc, deck for a presentation, or storyboard), chats and rolls of images and video, newest first, with app links and whether a doc has a public link. Pass cursor to read on. pins lists what every chat here reads, parent spaces included; files lists the space's Files, the documents every chat here can read; media lists the pictures, clips and sounds people brought into the space on purpose, newest 60 (media_more counts the rest; a picture's media_id is its image_id). collections lists how the space's images are sorted, with the groups in each, parent spaces included.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id"
],
"properties": {
"cursor": {
"type": "string",
"description": "next_cursor from the previous page."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Make a new doc in a space from your Markdown, for material a task should read (pass its id in doc_ids) or a text your human wants kept. It starts private to your human; the team sees it once shared or pinned. A body in a file on your disk: leave out content, then send the file to the upload_url you get, e.g. curl -T <path> '<upload_url>'; the answer is the new doc, and each send makes another. The link works for 15 minutes.
| Parameter | Type | Description |
|---|---|---|
| title * | string | |
| content | string | The doc body as Markdown. Leave out to send it from a file. |
| space_id * | string | A space id from list_spaces. |
{
"name": "create_doc",
"title": "Create doc",
"description": "Make a new doc in a space from your Markdown, for material a task should read (pass its id in doc_ids) or a text your human wants kept. It starts private to your human; the team sees it once shared or pinned. A body in a file on your disk: leave out content, then send the file to the upload_url you get, e.g. curl -T <path> '<upload_url>'; the answer is the new doc, and each send makes another. The link works for 15 minutes.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id",
"title"
],
"properties": {
"title": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"content": {
"type": "string",
"description": "The doc body as Markdown. Leave out to send it from a file."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Change a doc's text and nothing else in it. One passage: old_text and new_text. Add to the end: append_text. The whole body: content and updated_at from your read_doc, refused when anyone edited it since, so you never overwrite the team. The text it replaces stays in the doc's version history. Presentations and storyboards change only through a task.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | A doc id from get_task or list_space. |
| content | string | The new whole doc body as Markdown. |
| new_text | string | What replaces old_text. Empty deletes it. |
| old_text | string | The passage, copied exactly from read_doc. It must appear once: add nearby words if it repeats. |
| updated_at | string | updated_at from your read_doc. Needed with content; otherwise it refuses a doc edited since. |
| append_text | string | Markdown to add at the end of the doc. |
{
"name": "update_doc",
"title": "Update doc",
"description": "Change a doc's text and nothing else in it. One passage: old_text and new_text. Add to the end: append_text. The whole body: content and updated_at from your read_doc, refused when anyone edited it since, so you never overwrite the team. The text it replaces stays in the doc's version history. Presentations and storyboards change only through a task.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
},
"content": {
"type": "string",
"description": "The new whole doc body as Markdown."
},
"new_text": {
"type": "string",
"description": "What replaces old_text. Empty deletes it."
},
"old_text": {
"type": "string",
"minLength": 1,
"description": "The passage, copied exactly from read_doc. It must appear once: add nearby words if it repeats."
},
"updated_at": {
"type": "string",
"description": "updated_at from your read_doc. Needed with content; otherwise it refuses a doc edited since."
},
"append_text": {
"type": "string",
"minLength": 1,
"description": "Markdown to add at the end of the doc."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Pin a doc, presentation, storyboard, space file or space images to its space, so every chat in the space and its sub-spaces reads it: brand rules, a brief, a source the work must rest on. A doc still in its task chat is added to that chat's space first. A pin is team material: when it would share a private doc with the team or turn its reuse back on, this is refused; ask your human, then call again with share: true. A space file or image already belongs to its space, so it pins without asking.
| Parameter | Type | Description |
|---|---|---|
| share | boolean | true only once your human agreed to what the refusal named. |
| doc_id | string | A doc id from get_task or list_space. |
| space_id | string | With space_file_id or image_ids: the space that holds them. |
| image_ids | array | Instead of doc_id: images from upload_file's answer with space_id, in that space. |
| space_file_id | string | Instead of doc_id: a file from list_space files or upload_file's answer. |
{
"name": "pin",
"title": "Pin doc, file or images",
"description": "Pin a doc, presentation, storyboard, space file or space images to its space, so every chat in the space and its sub-spaces reads it: brand rules, a brief, a source the work must rest on. A doc still in its task chat is added to that chat's space first. A pin is team material: when it would share a private doc with the team or turn its reuse back on, this is refused; ask your human, then call again with share: true. A space file or image already belongs to its space, so it pins without asking.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"share": {
"type": "boolean",
"description": "true only once your human agreed to what the refusal named."
},
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "With space_file_id or image_ids: the space that holds them."
},
"image_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"maxItems": 100,
"minItems": 1,
"description": "Instead of doc_id: images from upload_file's answer with space_id, in that space."
},
"space_file_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "Instead of doc_id: a file from list_space files or upload_file's answer."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Stop new chats reading a pin, when a round changes direction. Take pin_id and space_id from list_space; a pin held by a parent space comes off that space and everything under it. The doc or file itself stays, with the same access.
| Parameter | Type | Description |
|---|---|---|
| pin_id * | string | |
| space_id * | string |
{
"name": "unpin",
"title": "Unpin doc",
"description": "Stop new chats reading a pin, when a round changes direction. Take pin_id and space_id from list_space; a pin held by a parent space comes off that space and everything under it. The doc or file itself stays, with the same access.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"pin_id",
"space_id"
],
"properties": {
"pin_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Sort images you sent to a space (upload_file with space_id) into its collections, as a drop in the app: each lands in the collection and group it fits, and images that fit none start a new collection. The answer says where each landed, with app links, and gives a drop_id: undo_drop takes the whole drop back within a day. Sorting looks at every image, so a big drop takes up to a minute.
| Parameter | Type | Description |
|---|---|---|
| name | string | What to call a new collection for images that fit none, such as the folder they came from. |
| space_id * | string | The space the images were sent to. |
| image_ids * | array | image_id values from upload_file's answers. |
| collection_id | string | One of this space's own collections from list_space (no from_space_id): sort into its groups only, as a drop on its page. |
{
"name": "add_images",
"title": "Add images to collections",
"description": "Sort images you sent to a space (upload_file with space_id) into its collections, as a drop in the app: each lands in the collection and group it fits, and images that fit none start a new collection. The answer says where each landed, with app links, and gives a drop_id: undo_drop takes the whole drop back within a day. Sorting looks at every image, so a big drop takes up to a minute.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"space_id",
"image_ids"
],
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "What to call a new collection for images that fit none, such as the folder they came from."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "The space the images were sent to."
},
"image_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"maxItems": 100,
"minItems": 1,
"description": "image_id values from upload_file's answers."
},
"collection_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "One of this space's own collections from list_space (no from_space_id): sort into its groups only, as a drop on its page."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Take back an add_images drop: the images it added leave their collections, wherever they were moved since, and collections it started and left empty are deleted. An image it took out that no collection or pin holds is deleted after a day; send it again to sort it.
| Parameter | Type | Description |
|---|---|---|
| drop_id * | string | drop_id from add_images' answer. |
{
"name": "undo_drop",
"title": "Undo a drop",
"description": "Take back an add_images drop: the images it added leave their collections, wherever they were moved since, and collections it started and left empty are deleted. An image it took out that no collection or pin holds is deleted after a day; send it again to sort it.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"drop_id"
],
"properties": {
"drop_id": {
"type": "string",
"minLength": 1,
"description": "drop_id from add_images' answer."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Copy a doc, presentation or storyboard to start the next round from, keeping the original as it is. The copy is private to your human and lands in the same space when they can open it; comments, versions and sharing stay behind. A storyboard's copy picks from the same roll, and a presentation's drops slides not written yet.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | A doc id from get_task or list_space. |
{
"name": "duplicate_doc",
"title": "Duplicate doc",
"description": "Copy a doc, presentation or storyboard to start the next round from, keeping the original as it is. The copy is private to your human and lands in the same space when they can open it; comments, versions and sharing stay behind. A storyboard's copy picks from the same roll, and a presentation's drops slides not written yet.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Rename a doc, presentation or storyboard, file it in a space, or set who can open it. visibility org opens it to the team (ask your human first); a doc still in its task chat is filed in the chat space for that. visibility private also takes it off the web and out of its space's pins, and only its creator can set it.
| Parameter | Type | Description |
|---|---|---|
| title | string | |
| doc_id * | string | A doc id from get_task or list_space. |
| space_id | string | A space id from list_spaces to file it in. |
| visibility | string | one of ["private","org"] |
{
"name": "update_doc_info",
"title": "Update doc info",
"description": "Rename a doc, presentation or storyboard, file it in a space, or set who can open it. visibility org opens it to the team (ask your human first); a doc still in its task chat is filed in the chat space for that. visibility private also takes it off the web and out of its space's pins, and only its creator can set it.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"doc_id"
],
"properties": {
"title": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"doc_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A doc id from get_task or list_space."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces to file it in."
},
"visibility": {
"enum": [
"private",
"org"
],
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": true
}
}Keep the answer a task's latest finished reply ends with as a doc of that task, word for word, with its sources and evidence, so another task can read it (doc_ids) or you can pin, share or export it. The opening line and progress notes it wrote between steps are left out.
| Parameter | Type | Description |
|---|---|---|
| title * | string | |
| task_id * | string |
{
"name": "save_reply_to_doc",
"title": "Save reply to doc",
"description": "Keep the answer a task's latest finished reply ends with as a doc of that task, word for word, with its sources and evidence, so another task can read it (doc_ids) or you can pin, share or export it. The opening line and progress notes it wrote between steps are left out.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id",
"title"
],
"properties": {
"title": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Nutcracker does the creative work: strategy, copy, naming, ideas, research-backed docs, presentations, storyboards, images and video. You bring the facts and publish the result; Nutcracker picks the method. - A task is a chat in one space. Find the space with list_spaces; when none fits, make one with create_space. Send a plain brief: what your human wants made and who it is for, in the words they or their client used. Context holds what is known: facts, numbers, sources, what the client said, and hard limits (dates, formats, mandatories, law). What Nutcracker knows about the brand reaches every task for that brand, in any space; the space's memory and pinned docs apply to every task in it. Name the brand in the brief. - Nutcracker sets the creative bar itself: work the best independent agencies would sign, that could win at Cannes or D&AD or run in the Super Bowl, surprising and remembered as this brand's, in whatever medium and register fit. Anything a brief adds to that narrows every option to it: a test a good answer must pass (that it can be proven or checked, that no rival could run it), your diagnosis of the problem, the kind of idea you expect. Leave those out; when your human or the client set one, quote it as theirs. What the brief leaves open and a client can arrange (a budget, a permit, a partner, a talent) is no reason to rule an idea out. Judge what comes back by that bar, not by how safe or easy to check it is. - list_work names the kinds of work and what each returns; name one in the brief when it fits. Ask for a structure (sections, counts, a template) only when your reader needs that exact one: a structure you prescribe replaces the one the method gives. - A task takes minutes: poll get_task with wait_seconds, and pass back the seen it gave you so it returns only what changed. needs_input means it waits on a choice; ask your human when it is a matter of taste, then answer with reply. Ask for revisions with reply too, so the chat keeps its history. While it runs, reply with what your human adds or corrects and the task takes it at its next step. - For another model's take on ideas, a script, lines or an insight, call reply with another_ai: a model from another lab writes its own version with the same method, it lands beside the first in the app, and the task says how they differ. list_models names the models. To steer the take, or before a first reply exists, say so in words in the brief or in reply ("ask GPT, focus on the hook"). get_task lists the skills a task used. - A task can't read other tasks. To hand work on, keep it as a doc (save_reply_to_doc, or a doc the task made) and pass its id in doc_ids. Pass the doc, not your summary of it: a summary hands on only what you picked from it. - A task sees your images and files only when you upload them: upload_file, send the file to its url, pass the file_id in files on start_task or reply. Documents the space should keep (a client's decks, research, brand book) go to upload_file with space_id: they join the space's Files, which every chat in it reads and the team sees. - Docs a task makes belong to its chat: get_task lists them, list_space shows them once filed in the space or pinned. Every doc starts private to your human. - pin makes a doc or a space file material every chat in its space reads (brand rules, a standing brief, a source). Pinning a doc in a team space shares it with the team, so pin is refused until your human agrees. - share_link publishes: anyone with the link opens it without an account until unshare. The link shows in the doc's Share panel. - Media spends the workspace credits; get_credits shows what is left. A task may make images itself; get_task shows what each cost. Image and video cards wait for you: run one with generate only after your human agrees to its price. A needs_input option with a credit price spends too: answer with it only after your human agrees. - update_doc changes a doc's text: one passage, an addition at the end, or
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
{
"name": "start_task",
"title": "Start task",
"description": "Start a creative task (writing, strategy, naming, ideas, research-backed docs) as a new Nutcracker chat in a space; what Nutcracker knows about the brand, the memory of the space and its pins apply. Returns task_id and the chat url. A task takes minutes: poll get_task until it is no longer running.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"brief",
"space_id"
],
"properties": {
"brief": {
"type": "string",
"minLength": 1,
"description": "What to make and who it is for, in plain words, as your human or their client would say it."
},
"files": {
"type": "array",
"items": {
"type": "string",
"pattern": "^(media|doc):[0-9a-f-]{36}$|^clip:[\\w-]+\\.[\\w-]+$"
},
"maxItems": 16,
"description": "file_id values from sending files to upload_file urls."
},
"model": {
"type": "string",
"minLength": 1,
"description": "A name from list_models with kind writer and chat true, only when your human named one (\"run it on Opus\"). Without it the task runs on the workspace default, which suits most work."
},
"memory": {
"enum": [
"normal",
"dont-add",
"no-memory"
],
"type": "string",
"description": "What the task does with memory, as the chat's own setting. normal: Uses memory and adds what it learns. In a team space, it helps the team’s chats. dont-add: Uses memory. Nothing from this chat is kept for later or for the team. no-memory: Doesn’t use or add to memory. Works only from what you give it. Default normal."
},
"context": {
"type": "string",
"description": "What is known: facts, numbers, sources, what the client said and hard limits. Not your reading of them, and no test of your own for a good answer."
},
"doc_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"maxItems": 10,
"description": "Docs, presentations or storyboards the task must read (ids from get_task, list_space or create_doc)."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}{
"name": "get_task",
"title": "Get task",
"description": "Where a task stands: running, needs_input (answer the question with reply), done, or failed. While running, progress names the step in flight (research, skill, ...; null while it thinks or writes the reply), its latest headline, and how many sources research has read. Returns the answer the latest reply ends with (a failed task: all it wrote) with evidence as links and [image card: name] where a card stands, the space the task is in now (null outside any space; a chat can move), the sources it cites, the skills it used, the brand it was for, the other AI behind a take, steers_taken (messages sent while it ran that the reply took), the documents the task made (id, title, url), its images, video and sound with file urls and the credits each spent, and the image and video cards of the latest reply with their price (made: true when the card already has its picture or clip, so generate would buy another take): run one with generate once your human agrees to the price. memory_suggestions lists lines waiting for your human's yes before the space's memory keeps them; ask them, then answer with answer_memory.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id"
],
"properties": {
"seen": {
"type": "string",
"description": "The seen value from your last get_task: leaves out the reply, sources and cards you already read, and media that has not changed. Leave it out to read the cards and their prices again."
},
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A task_id, or a chat id from list_space."
},
"all_sources": {
"type": "boolean",
"description": "List every source the task saw (sources_seen counts them), not only those the reply cites."
},
"wait_seconds": {
"type": "number",
"minimum": 0,
"description": "Hold the call while the task, or once it is done its media, is still going, up to 45 seconds; it returns as soon as that ends. Use it instead of polling fast."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}{
"name": "upload_file",
"title": "Upload file",
"description": "Get a link to send one image, video or document from your disk (logo, screenshot, product shot, PDF) for a task to work from. Send the file with an HTTP PUT, e.g. curl -T <path> '<upload_url>'; the answer is JSON with the file_id to pass in files on start_task or reply. The link works for 15 minutes. One file_id works for any number of tasks. A document up to 100 MB, an image up to 20 MB. A video (up to 1 GB) or sound (up to 200 MB) needs size_bytes, its exact size: the answer gives its file_id (or media_id) at once, and the PUT must carry the headers it names, e.g. curl -T <path> -H 'Content-Type: video/mp4' '<upload_url>'. Upload an image or video right before the task that uses it: about 20 can wait unsent, and waiting ones also block your human uploading in the app. A large scan can take minutes to read; start_task says when it is not ready yet. With space_id, a document joins that space's Files instead: every chat in the space reads it, the team sees it, and pin can make it required reading. The answer comes once it is read, with its space_file_id; no file_id is needed for tasks there. A long read answers reading: true, and list_space shows the file when it is done. A PNG, JPEG, WebP, GIF or SVG image with space_id goes to that space and answers its image_id: add_images sorts it into the space's collections, pin makes it material every chat reads, and create_element makes it an @element. An MP4, MOV or WebM video or an MP3, WAV or M4A sound with space_id answers a media_id for create_element. An upload nothing holds is deleted after a day.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"filename"
],
"properties": {
"filename": {
"type": "string",
"maxLength": 255,
"minLength": 1,
"description": "Its name with extension, which sets how it is read."
},
"space_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A space id from list_spaces, to keep a document in its Files or an image in its images rather than give it to one task."
},
"size_bytes": {
"type": "integer",
"maximum": 9007199254740991,
"description": "A video or sound: its exact size in bytes (wc -c < file), which the storage link is signed for.",
"exclusiveMinimum": 0
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}