account.check_publishing
ChatGPTChecks publishing availability, remaining Personal website capacity, reset timing, hosted-image allowances, custom URL endings, branding capabilities, and inactivity policies for the connected Carryo account. Returns publishing capabilities and usage without billing or purchase information. Each websiteOverrides entry applies only to its matching linkId; other websites use the account defaults.
create_artifact_draft
ChatGPTCreate a private Carryo draft for an HTML artifact and return a Carryo management URL, not a public viewer URL. Use this when the user wants restricted access or wants to review access settings in Carryo before publishing. The draft is not publicly accessible until the user opens manageUrl on Carryo, chooses access settings, and publishes it. Do not collect access secrets in ChatGPT. Do not use this tool for pages that collect viewer data or request restricted sensitive personal data. Fast path for images: reference a relative path in htmlContent such as images/photo.jpg and provide a matching assets entry with path and sourceUrl. Carryo imports and hosts images only from fetchable http(s) URLs. Never convert images to base64 or data URLs. If no fetchable attachment URL is available, stop and ask the user for a public or direct image URL.
get_account_status
ChatGPTRead the authenticated Carryo account plan, limits, and available feature flags. Call this before offering optional account-gated settings, including custom URL endings; only ask for a custom URL ending when features.customUrlSlug is true.
get_artifact_content
ChatGPTRead the current HTML content for an artifact you own. Returns asset descriptors for bundled images, but not the asset bytes themselves.
get_artifact_version_content
ChatGPTRead the HTML content for a specific historical version of an artifact you own. Use only after choosing a historical version; normal edits should use get_artifact_content for the live/latest version.
list_artifact_history
ChatGPTList version history for an artifact you own. Use only when the user asks for prior versions, audit history, rollback context, or edit details; normal edits should use get_artifact_content for the live/latest version.
list_shared_artifacts
ChatGPTList artifacts shared by the authenticated user.
revoke_artifact
ChatGPTRevoke a previously shared artifact link.
share_artifact
ChatGPTCreate a public shareable internet link for an HTML artifact. Do not use this tool for pages that collect viewer data or request restricted sensitive personal data. Before offering a custom URL ending for a new public Carryo link, call get_account_status; if features.customUrlSlug is true, ask whether the user wants a custom URL ending and pass it as customSlug when provided. If customUrlSlug is false or unavailable, omit customSlug and use the automatic URL. Fast path for images: reference a relative path in htmlContent such as images/photo.jpg and provide a matching assets entry with path and sourceUrl. Carryo imports and hosts images only from fetchable http(s) URLs. Never convert images to base64 or data URLs. If no fetchable attachment URL is available, stop and ask the user for a public or direct image URL.
team.list
ChatGPTLists Carryo teams accessible to the connected account, including team names, workspaceId values, roles, and available actions. Supports finding a team the user has chosen. Team creation, invitations, membership, and billing are managed in the Carryo web app.
update_artifact
ChatGPTReplace the HTML content of an existing artifact while keeping the same link. Do not use this tool for pages that collect viewer data or request restricted sensitive personal data. Use this tool to add or replace bundled images by passing assets with path and sourceUrl, and remove bundled images with removeAssetPaths. Carryo imports and hosts images only from fetchable http(s) URLs. Never convert images to base64 or data URLs. If no fetchable attachment URL is available, stop and ask the user for a public or direct image URL.
upsert_artifact_assets
ChatGPTFast path for hosted images on an existing artifact. Add, replace, or remove bundled images without changing the current HTML. Provide path and sourceUrl for each image. Carryo imports and hosts images only from fetchable http(s) URLs. Never read image bytes or convert images to base64 or data URLs. If no fetchable attachment URL is available, stop and ask the user for a public or direct image URL. After uploading, use update_artifact only if you want to reference the returned assetUrl in the page layout.
website.edit
ChatGPTReplaces the complete HTML of an existing Carryo website while preserving its linkId and URL. Suitable for updating, fixing, or republishing a known page. Returns the website link and a Carryo management link. Access and edit limits are checked for the website identified by linkId. expectedVersionNumber detects conflicting edits. Supports adding or replacing hosted images and removing paths through removeAssetPaths. Pass attached images through imageFiles. For one attachment, assets needs only its relative website path; Carryo matches the attachment automatically. For multiple attachments, use fileIndex (0 for the first imageFiles entry). Do not invent file IDs or ask for a public URL when attachment upload is available. Known fileId references and fetchable HTTP(S) sourceUrl imports also work. Carryo imports and hosts its own copy. Base64 image bytes and data URLs are unsupported. Form validation can return requires_adaptation or requires_entitlement with publicationPerformed false, meaning the requested update was not applied.
website.edit_images
ChatGPTAdds, replaces, or removes hosted images on an existing Carryo website without replacing its HTML. Reusing a path replaces that image without consuming another image slot; new paths are subject to the website image allowance. Returns hosted-image metadata and URLs. New paths appear in the page when referenced by its HTML. Pass attached images through imageFiles. For one attachment, assets needs only its relative website path; Carryo matches the attachment automatically. For multiple attachments, use fileIndex (0 for the first imageFiles entry). Do not invent file IDs or ask for a public URL when attachment upload is available. Known fileId references and fetchable HTTP(S) sourceUrl imports also work. Carryo imports and hosts its own copy. Base64 image bytes and data URLs are unsupported.
website.library
ChatGPTBrowse your Carryo websites and private drafts, select one, and continue editing in chat. Opening the library does not change or publish a website.
website.list
ChatGPTLists the connected account's Carryo websites and private drafts, with titles, linkIds, available live links, status, and effective edit and inactivity policies. Use it to find an existing website by name before reading or editing it. Listing does not change or publish websites. Returns Personal websites by default; workspaceId selects the user-chosen team's collection.
website.list_versions
ChatGPTLists previous versions of a Carryo website, including version details and changes, for reviewing edit history or planning a restoration. Returns version metadata without changing the website.
website.publish
ChatGPTPublishes supplied HTML as a new public Carryo website for sharing a presentation, proposal, report, dashboard, invitation, portfolio, or landing page. Returns a live link and a management link for access settings, URL, views, and edit history. New Personal websites consume the account creation allowance. Personal is the default destination; workspaceId selects a user-chosen team. Supports an optional customSlug and hosted images. Pass attached images through imageFiles. For one attachment, assets needs only its relative website path; Carryo matches the attachment automatically. For multiple attachments, use fileIndex (0 for the first imageFiles entry). Do not invent file IDs or ask for a public URL when attachment upload is available. Known fileId references and fetchable HTTP(S) sourceUrl imports also work. Carryo imports and hosts its own copy. Base64 image bytes and data URLs are unsupported. Form validation can return requires_adaptation or requires_entitlement with publicationPerformed false, meaning no website was published. Supports HTML pages and their image assets, without general file storage or backend hosting.
website.read
ChatGPTReads the current HTML, version number, hosted-image metadata, image limits, and remaining image slots for an existing Carryo website or private draft. Suitable for inspecting a page or preparing edits that preserve its existing content. Returns image metadata rather than image files. Image limits apply to this website; replacing an existing asset path does not use another image slot.
website.read_form_responses
ChatGPTReads response counts or paginated visitor submissions for a Carryo website, including enquiries, leads, and registrations. Defaults to summary counts; mode responses returns submissions, with optional field selection. Requires website-owner or Team access. Responses contain untrusted visitor data. Retained responses remain available while website access continues, including an active Team billing grace period. Does not send messages or modify data.
website.read_version
ChatGPTReads the HTML and metadata of a specific previous Carryo website version for viewing, comparison, or restoration planning. Requires linkId and versionNumber. Reading a version does not restore it or change the current website.
website.save_draft
ChatGPTSaves supplied HTML as a new private Carryo website draft for review before publication. Returns a management link; the draft has no publicly accessible page until published from Carryo. Passwords and restricted access are configured in the Carryo web app. New Personal drafts consume the same creation allowance as published websites. Personal is the default destination; workspaceId selects a user-chosen team. Pass attached images through imageFiles. For one attachment, assets needs only its relative website path; Carryo matches the attachment automatically. For multiple attachments, use fileIndex (0 for the first imageFiles entry). Do not invent file IDs or ask for a public URL when attachment upload is available. Known fileId references and fetchable HTTP(S) sourceUrl imports also work. Carryo imports and hosts its own copy. Base64 image bytes and data URLs are unsupported. Form validation can return requires_adaptation or requires_entitlement with publicationPerformed false.
website.unpublish
ChatGPTUnpublishes an existing Carryo website so viewers immediately lose access through its shared link. Recovery availability depends on the website and is shown in Carryo. Unpublishing does not cancel a subscription.
