Kive MCP tools: every tool the server exposes

The Kive MCP server exposes 28 tools for creating product images and video, importing products, searching a workspace, and organising the results. Each one is listed below by its exact tool name.

All 28 tools at a glance

Every tool the Kive MCP server exposes. Each name links to its full entry below.
ToolWhat it does
generate_product_imageGenerates product images from a saved product, a saved model, or a plain brief. Can return a credit estimate instead of spending anything.
generate_product_videoGenerates product video from saved products and models, optionally driven by a video preset.
edit_imageEdits an existing Kive image from a natural-language instruction, keeping the rest of the frame intact.
generate_prompt_from_imageReads one image and writes the prompt that would recreate its look, for reuse across other products.
create_product_in_kiveCreates a product from exactly one source: an e-commerce product page URL, an image URL, a local file, or a completed upload handle.
create_product_image_upload_urlIssues an upload URL for one local product image, for cases where the agent holds the file rather than a link.
confirm_product_image_uploadConfirms an upload finished so the image can be attached to a product.
show_product_image_upload_widgetFallback that renders a browser upload widget when a direct upload is blocked.
create_character_in_kiveCreates a reusable character model from reference images of the same person, so the same face carries across shots.
list_workspacesLists the Kive workspaces the connected account can reach, with their ids. Most flows start with this call.
find_productsSearches saved products by name, category or description.
find_modelsSearches saved AI models: characters and trained brand styles as well as products.
find_generationsSearches images and videos already generated in the workspace.
find_boardsLists boards and the assets saved on a given board.
find_studiosLists or searches studios: the published Kive catalog plus the workspace’s own custom studios.
recommend_studiosReturns studios matched to a product that is still being created, as a visual contact sheet to choose from.
find_video_presetsLists video presets available for product-video generation.
check_image_generation_statusChecks one image generation without rendering it. For headless use.
check_video_generation_statusThe same status check for a video generation.
check_character_creation_statusPolls a character-model creation job until it is ready.
show_kive_imageRenders a finished image inline in chat. This is the tool that owns final image cards.
show_kive_videoRenders a finished video inline in chat.
create_kive_boardCreates an empty board, for a moodboard or a campaign.
update_kive_boardRenames a board, edits its description, or moves it under another board.
move_kive_board_itemsMoves saved images or videos from one board to another.
kive_pingChecks that the MCP server itself is reachable.
kive_graphql_statusChecks that the server can reach the Kive API behind it.
check_kive_auth_statusChecks the identity the server is authenticated as. Called only after another tool reports an auth error.

Create and edit visuals

The four tools that produce something new. Each one starts a durable job, so an assistant can begin a render and collect it later.

  • generate_product_image

    Generates product images from a saved product, a saved model, or a plain brief. Can return a credit estimate instead of spending anything.

    Inputs: Required: workspaceId, plus a subject — productId, productQuery, modelIds or brief. Optional studioId, aspectRatio, samples, mode, styleImageUrls and estimateOnly.

    Ask for it like this:Shoot my ceramic mug in the Cream studio, 4:5, one image.

  • generate_product_video

    Generates product video from saved products and models, optionally driven by a video preset.

    Inputs: Required: workspaceId, plus a saved model — productId, productQuery or modelIds. A brief alone cannot start a video. Optional videoPresetId, duration, aspectRatio, withAudio and estimateOnly.

    Ask for it like this:Turn that hero shot into a five-second product clip.

  • edit_image

    Edits an existing Kive image from a natural-language instruction, keeping the rest of the frame intact.

    Inputs: Required: workspaceId and instruction, plus the source image as generationId, outputId or imageUrl.

    Ask for it like this:Make the background warmer and remove the shadow.

  • generate_prompt_from_image

    Reads one image and writes the prompt that would recreate its look, for reuse across other products.

    Inputs: Required: imageUrl, a publicly reachable https image URL.

    Ask for it like this:Describe the style of this reference so I can reuse it.

Bring products and characters in

Kive generates from saved products rather than from prompts alone, so most workflows start here. A product can come from a store URL, an image URL, or a file upload.

  • create_product_in_kive

    Creates a product from exactly one source: an e-commerce product page URL, an image URL, a local file, or a completed upload handle.

    Inputs: Required: workspaceId, plus exactly one source — productUrl, imageUrl(s), imageFilePath(s) or uploadedImageHandle(s). Optional productName and brief.

    Ask for it like this:Add this product to Kive: <your product page URL>

  • create_product_image_upload_url

    Issues an upload URL for one local product image, for cases where the agent holds the file rather than a link.

    Inputs: Required: workspaceId, fileName and contentType. Optional productName and brief.

    Ask for it like this:Upload these three photos of the bottle as one product.

  • confirm_product_image_upload

    Confirms an upload finished so the image can be attached to a product.

    Inputs: Required: workspaceId, uploadedImageHandle and the upload’s httpStatus.

    Ask for it like this:Used automatically after an upload completes.

  • show_product_image_upload_widget

    Fallback that renders a browser upload widget when a direct upload is blocked.

    Inputs: Nothing required. Pass the fallbackUploadWidget reference returned by create_product_image_upload_url.

    Ask for it like this:Used automatically when a direct upload fails.

  • create_character_in_kive

    Creates a reusable character model from reference images of the same person, so the same face carries across shots.

    Inputs: Required: workspaceId, plus reference images of one person as imageUrl(s), imageFilePath(s) or uploadedImageHandle(s). Optional characterName.

    Ask for it like this:Make a character model from these photos of our founder.

Find what the workspace already holds

Read-only lookups. An assistant asked to show a library uses these and never touches a generation tool.

  • list_workspaces

    Lists the Kive workspaces the connected account can reach, with their ids. Most flows start with this call.

    Inputs: Nothing required.

    Ask for it like this:Which Kive workspaces do I have?

  • find_products

    Searches saved products by name, category or description.

    Inputs: Required: workspaceId. Optional query.

    Ask for it like this:Show me the fragrances in my catalog.

  • find_models

    Searches saved AI models: characters and trained brand styles as well as products.

    Inputs: Required: workspaceId. Optional query and modelType.

    Ask for it like this:List my trained brand styles.

  • find_generations

    Searches images and videos already generated in the workspace.

    Inputs: Required: workspaceId. Optional assetType of IMAGE, VIDEO or ALL.

    Ask for it like this:Show the videos I generated last week.

  • find_boards

    Lists boards and the assets saved on a given board.

    Inputs: Required: workspaceId. Optional boardQuery or boardId.

    Ask for it like this:What is on my spring campaign board?

Pick a creative direction

Studios are saved scenes that bundle lighting, framing and environment. They are how output stays consistent without prompt engineering.

  • find_studios

    Lists or searches studios: the published Kive catalog plus the workspace’s own custom studios.

    Inputs: Required: workspaceId. Optional creative-direction query.

    Ask for it like this:Find a clean e-commerce studio for skincare.

  • recommend_studios

    Returns studios matched to a product that is still being created, as a visual contact sheet to choose from.

    Inputs: Required: jobId from product creation, and workspaceId.

    Ask for it like this:Which studios suit this product?

  • find_video_presets

    Lists video presets available for product-video generation.

    Inputs: Nothing required. Optional query.

    Ask for it like this:What video presets can I use?

Follow jobs and show results

Generation is asynchronous. These tools separate checking a job from rendering its output, so headless pipelines and chat surfaces can use the same server.

  • check_image_generation_status

    Checks one image generation without rendering it. For headless use.

    Inputs: Required: generationId and workspaceId. Optional waitMs.

    Ask for it like this:Is that render finished yet?

  • check_video_generation_status

    The same status check for a video generation.

    Inputs: Required: generationId and workspaceId. Optional waitMs.

    Ask for it like this:Is the clip done?

  • check_character_creation_status

    Polls a character-model creation job until it is ready.

    Inputs: Required: the character creation jobId, and workspaceId.

    Ask for it like this:Is my character model trained?

  • show_kive_image

    Renders a finished image inline in chat. This is the tool that owns final image cards.

    Inputs: Nothing required. Pass generationId or jobId with workspaceId, or a direct imageUrl.

    Ask for it like this:Show me the result.

  • show_kive_video

    Renders a finished video inline in chat.

    Inputs: Nothing required. Pass generationId with workspaceId, or a direct videoUrl.

    Ask for it like this:Play the clip here.

Organise boards

Boards are where generated work is kept and shared, so an agent can file its own output rather than leaving it loose.

  • create_kive_board

    Creates an empty board, for a moodboard or a campaign.

    Inputs: Required: workspaceId and title. Optional parentBoardId to nest it.

    Ask for it like this:Make a board called Autumn Launch.

  • update_kive_board

    Renames a board, edits its description, or moves it under another board.

    Inputs: Required: workspaceId and boardId, plus the fields being changed — title, description, parentBoardId or moveToTopLevel.

    Ask for it like this:Rename that board to Autumn Launch 2026.

  • move_kive_board_items

    Moves saved images or videos from one board to another.

    Inputs: Required: workspaceId, boardItemIds and targetBoardId.

    Ask for it like this:Move these three shots to the launch board.

Connection checks

Diagnostics, used when something is not responding. They are not part of a normal creative flow.

  • kive_ping

    Checks that the MCP server itself is reachable.

    Inputs: Nothing required. Optional message to echo back.

    Ask for it like this:Is the Kive MCP server up?

  • kive_graphql_status

    Checks that the server can reach the Kive API behind it.

    Inputs: Nothing required.

    Ask for it like this:Can the connector reach Kive?

  • check_kive_auth_status

    Checks the identity the server is authenticated as. Called only after another tool reports an auth error.

    Inputs: Nothing required.

    Ask for it like this:Which Kive account is this connector using?

Recipes: whole jobs, end to end

Individual tools are the vocabulary. These are the sentences – the call sequences an agent runs to finish a real piece of work. Each step links to the tool it uses.

  • Shoot a whole product catalogue in one scene

    You say:Shoot everything in my Kive catalogue in the same clean studio, 4:5.

    1. list_workspacesResolve which Kive workspace to work in. Every later call needs its id.
    2. find_productsList the saved products to shoot, optionally narrowed by a search query.
    3. find_studiosPick one studio so every product lands in the same lighting and set.
    4. generate_product_imageStart a generation per product, passing the same studioId and aspect ratio each time.
    5. check_image_generation_statusPoll each generation until it reports done. Generation is asynchronous.
    6. show_kive_imageRender each finished image inline once its job completes.

    You get: One image per product, all in the same scene, rendered in the chat as they finish.

  • Generate ad-creative variants of one product

    You say:Give me four ad variants of the ceramic mug, each in a different scene.

    1. list_workspacesResolve the workspace id. Every call below is workspace-scoped and fails without it.
    2. find_productsLocate the one product the variants are built from.
    3. find_studiosChoose several contrasting studios so the variants differ by scene, not by prompt wording.
    4. generate_product_imageRun one generation per studio against the same productId. Pass estimateOnly first to see the credit cost.
    5. check_image_generation_statusPoll each of the variants until every job reports done.
    6. show_kive_imageRender the finished set side by side for a pick.

    You get: Four takes on the same product in different studios, ready to test as creative.

  • Produce product video from a saved product

    You say:Make a five-second clip of the mug using one of the video presets.

    1. list_workspacesResolve the workspace id. Every call below is workspace-scoped and fails without it.
    2. find_productsPick the saved product the clip is generated from.
    3. find_video_presetsList the available motion presets. This is the one lookup that needs no workspaceId.
    4. generate_product_videoStart the video job with a productId and a videoPresetId, plus duration and aspect ratio.
    5. check_video_generation_statusPoll until the video job finishes. Video takes longer than stills.
    6. show_kive_videoPlay the finished clip inline.

    You get: A rendered product clip, playable in the chat.

  • Import a product from a store URL, then shoot it

    You say:Add this product to Kive and show me what it looks like in a few scenes.

    1. list_workspacesResolve the workspace id. Every call below is workspace-scoped and fails without it.
    2. create_product_in_kiveImport from the product page URL. Pass exactly one source: productUrl, an image, or an upload handle.
    3. recommend_studiosPass the jobId returned by the import to get studios matched to that specific product.
    4. generate_product_imageShoot the new product in whichever recommended studio was chosen.
    5. check_image_generation_statusPoll the generation until it reports done.
    6. show_kive_imageRender the first shots of the newly imported product.

    You get: A saved product in the workspace, plus first shots in studios matched to it.

Common questions