fuzz_answer_brand_question
ChatGPTSubmits the user’s answer to a pending brand onboarding question identified by runId and questionId. Corrections replace the details onboarding found, and onboarding then continues reading the brand’s public websites and social pages. brandId is optional while the brand profile does not exist yet.
fuzz_cancel_run
ChatGPTRequests cancellation of an asynchronous run. Work that already finished, and credits it already used, are not reversed.
fuzz_complete_upload
ChatGPTFinalizes an uploaded file by uploadId and stores it as a workspace asset.
fuzz_connect_node_input
ChatGPTConnects a source node or stored asset from the same workspace to one of the target node’s supported input slots. Requires the node’s latest revision. Does not generate.
fuzz_create_brand
ChatGPTStarts brand onboarding from at least one website or social URL plus optional factual context. Onboarding runs asynchronously, can ask follow-up questions and can spend credits. Returns a runId.
fuzz_create_node
ChatGPTCreates and places a text, image, video, audio or post draft node on the workspace canvas, with optional initial input connections. Saves a draft only; it does not generate.
fuzz_create_workspace
ChatGPTCreates a named workspace under an existing brand.
fuzz_disconnect_node_input
ChatGPTRemoves one input connection from a node by connectionId. The source node or asset itself is kept. Requires the node’s latest revision.
fuzz_download_asset
ChatGPTPrepares a 15-minute private download of one stored asset’s original file. Returns a URL with the private request headers needed to fetch it, and an equivalent downloadUrl that opens directly in a browser. Both are credentials for that one file.
fuzz_export_node
ChatGPTPrepares a 15-minute private ZIP export of one canvas node. The ZIP is built when the link is fetched; nothing is saved in the workspace. Returns a URL with the private request headers needed to fetch it, and an equivalent downloadUrl that opens directly in a browser.
fuzz_export_nodes
ChatGPTPrepares a 15-minute private ZIP export of several canvas nodes from one workspace. The ZIP is built when the link is fetched; nothing is saved in the workspace. Returns a URL with the private request headers needed to fetch it, and an equivalent downloadUrl that opens directly in a browser.
fuzz_generate_node
ChatGPTStarts generation from a node’s saved prompt, model, settings and connections. Connected upstream nodes it depends on can run too, and new outputs replace what those nodes currently show. Requires the node’s latest revision. Spends credits under the user’s plan. Returns a runId for an asynchronous run.
fuzz_get_asset
ChatGPTReturns a stored asset’s name, MIME type, size, dimensions and, for text assets, its text content.
fuzz_get_brand
ChatGPTReturns the creative context of one brand: tagline, description, sectors, website domains, logo usages, colors, fonts, voice, products and audience. Use it to keep content on brand; generation applies the brand logos itself. It does not return contact details, social accounts or media links.
fuzz_get_brand_quota
ChatGPTReturns how many brands the user has, the brand limit of their current plan, how many more they can create and whether a new brand can be created now.
fuzz_get_node
ChatGPTReturns a canvas node’s saved draft (prompt, model, settings), revision, supported inputSlots, connections, placement and output asset IDs.
fuzz_get_run
ChatGPTReturns the status, current step, pending question or approval, error, output node and asset IDs and, for chat runs, the assistant’s reply text of an asynchronous brand, chat or generation run. A run continues if the client disconnects. In clients that support MCP Apps, completed image, video and audio outputs are shown in an interactive preview.
fuzz_get_workspace
ChatGPTReturns one workspace and, optionally, its chat conversations that can be continued. Does not change what the user sees in the Fuzzbucket app.
fuzz_list_brands
ChatGPTLists the Fuzzbucket brands owned by the signed-in user. A brand holds the identity, products, audience and style used by creative work. Brands with ready=true can be used for creative work; a brand that is still being set up or whose setup failed has ready=false and a note explaining why.
fuzz_list_models
ChatGPTLists the models available to the user for a workspace: ID, label, provider, generation modes and a credit estimate for each. Filter by mediaType; pass modelId to get that model's supported settings (aspect ratios, resolutions, durations, reference limits) and full credit estimate.
fuzz_list_workspace_contents
ChatGPTLists canvas nodes and stored assets in a workspace, with name search and pagination. Node IDs and asset IDs are different identifiers.
fuzz_list_workspaces
ChatGPTLists workspaces for a brand. A workspace holds an orchestrator chat and a canvas of nodes.
fuzz_prepare_upload
ChatGPTPrepares a short-lived transfer for uploading a reference file of up to 100 MB into a workspace. Returns an uploadId, URL and private request headers for a multipart upload.
fuzz_preview_assets
ChatGPTReturns compact previews of up to four stored assets from one workspace: small thumbnails as image content for images and videos (a frame from the video), plus name, type and size for audio, text and other files. In clients that support MCP Apps, the previews are shown in an interactive gallery. Original files are available through fuzz_download_asset.
fuzz_preview_brand_logos
ChatGPTReturns small thumbnails of up to five logos of one brand as image content, with each logo’s usage (for example primary or icon). Read-only.
fuzz_read_chat
ChatGPTReturns persisted user and assistant messages from a workspace chat conversation, with pagination.
fuzz_respond_to_chat_approval
ChatGPTSubmits the user’s approve or decline decision, with optional feedback, for a pending orchestrator approval identified by runId and questionId. Approving can start generation and spend credits.
fuzz_send_chat_message
ChatGPTSends a creative brief, with optional node or asset references, to the workspace orchestrator. The orchestrator can create, edit and generate canvas content, can use public web pages as references, and can spend credits. Returns conversationId and runId for an asynchronous run.
fuzz_update_node_input
ChatGPTUpdates a node’s saved prompt, model or settings. Omitted fields are kept. Requires the node’s latest revision. Does not generate.
