Carryo Website Publisher

Save a Private Website Draft

website.save_draft

Saves 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.

Input Schema

TableJSON Schema

Name	Required	Description
`forms`	No	Optional definitions for JavaScript/React forms using window.CarryoForms.submit(key, values), which resolves on acceptance and rejects on failure. Stable keys and field names identify forms across edits. Static collection forms are inferred from data-carryo-form="key" and named controls without duplicate definitions; placeholder submit handlers can block collection. Local calculator/filter forms use data-carryo-local and do not collect responses. Existing external endpoints retain their destination. Visitor acknowledgement is disabled unless explicitly enabled.
`assets`	No	Optional image assets to add or replace. Each entry requires a relative website path. With one imageFiles attachment, path alone uses that attachment. Otherwise select exactly one source: fileIndex (zero-based imageFiles position), a known fileId, or a fetchable HTTP(S) sourceUrl. Never guess generated file IDs. Existing images are preserved when omitted; replacing an existing path does not use another slot. Base64 bytes and data URLs are unsupported.
`fileName`	Yes	Short internal file name, for example client-proposal.html, board-deck.html, report.html, or landing-page.html.
`expiresAt`	No	Optional ISO-8601 expiration timestamp
`customSlug`	No	Optional user-chosen URL ending using lowercase letters, numbers, and hyphens. An automatic URL is generated when omitted.
`imageFiles`	No	Optional image attachments supplied through the host's file upload support. The host supplies file_id and download_url. Map each attachment to a website path in assets: with one attachment, path alone is sufficient; with multiple attachments, use fileIndex. The assistant does not need to know generated file IDs or download URLs. Temporary URLs are import sources, not hosted image URLs. Clients without file input support can omit this field.
`htmlContent`	Yes	Complete HTML for the private Carryo draft page, presentation, slide deck, proposal, report, landing page, dashboard, invitation, portfolio, or one-page website.
`workspaceId`	No	Optional exact workspaceId of the Carryo team explicitly selected by the user. The default destination is Personal when omitted.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No
`forms`	No
`status`	No
`draftId`	No	Carryo private draft identifier
`message`	No
`guidance`	No
`expiresAt`	No	Optional ISO-8601 expiration timestamp
`manageUrl`	No	Carryo URL where the user can review access settings and publish the draft
`workspaceId`	No	Workspace that owns the draft; omitted for Personal
`currentVersionNumber`	No
`publicationPerformed`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 25, 2026

changedInput schema / properties / assets / description

Previous value: -"Optional image assets to add or replace. Each entry requires a relative HTML path and exactly one of fileId (matching imageFiles[].file_id) or sourceUrl (a fetchable HTTP(S) image URL). Existing images are preserved when omitted. The hosted-image allowance applies to the final website collection; replacing an existing path does not use another slot. Base64 bytes and data URLs are unsupported."New value: +"Optional image assets to add or replace. Each entry requires a relative website path. With one imageFiles attachment, path alone uses that attachment. Otherwise select exactly one source: fileIndex (zero-based imageFiles position), a known fileId, or a fetchable HTTP(S) sourceUrl. Never guess generated file IDs. Existing images are preserved when omitted; replacing an existing path does not use another slot. Base64 bytes and data URLs are unsupported."

changedInput schema / properties / assets / items / properties / fileId / description

Previous value: -"Attachment file_id matching a host-supplied imageFiles entry. Mutually exclusive with sourceUrl."New value: +"Known attachment file_id matching an imageFiles entry. Prefer fileIndex if the host-generated ID is not visible. Mutually exclusive with fileIndex and sourceUrl."

addedInput schema / properties / assets / items / properties / fileIndex

Added value: +{
+  "description": "Zero-based position in imageFiles: 0 selects its first attachment. Use this when the host generates file IDs during upload. May be omitted when imageFiles contains exactly one attachment. Mutually exclusive with fileId and sourceUrl.",
+  "maximum": 19,
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / assets / items / properties / sourceUrl / description

Previous value: -"Fetchable HTTP(S) image URL for Carryo to import and host. Mutually exclusive with fileId. Data URLs and base64 bytes are unsupported."New value: +"Fetchable HTTP(S) image URL for Carryo to import and host. Mutually exclusive with fileId and fileIndex. Data URLs and base64 bytes are unsupported."

changedInput schema / properties / imageFiles / description

Previous value: -"Optional image attachments supplied by a compatible host, with file_id and download_url. Each attachment is mapped to a relative HTML path by an assets entry with the matching fileId. Temporary download URLs are import sources, not hosted image URLs. Clients without file input support can omit this field."New value: +"Optional image attachments supplied through the host's file upload support. The host supplies file_id and download_url. Map each attachment to a website path in assets: with one attachment, path alone is sufficient; with multiple attachments, use fileIndex. The assistant does not need to know generated file IDs or download URLs. Temporary URLs are import sources, not hosted image URLs. Clients without file input support can omit this field."

First observedSep 10, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only minimal annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description carries the burden and delivers: it reveals the return behavior (management link), the visibility lifecycle (no public page until published), quota impact (Personal drafts consume creation allowance), hosting semantics (Carryo imports its own copy), unsupported inputs (base64/data URLs), and error states (requires_adaptation/requires_entitlement with publicationPerformed false). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly 200 words is long, but the tool has 8 parameters with intricate attachment and form semantics, and nearly every sentence carries a distinct fact (allowance, hosting, exclusions, error codes). The core purpose is front-loaded and the parameter guidance flows logically, though a couple of sentences could be merged without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool, the description covers the full call surface: primary purpose, return value, visibility behavior, quota, destination selection, image attachment routing options, unsupported formats, and validation error responses. The output schema exists and the description still mentions the management link and publicationPerformed flag, so nothing critical is left to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining the cross-parameter relationship between imageFiles and assets ('with multiple attachments, use fileIndex'), the anti-pattern warning ('Do not invent file IDs or ask for a public URL'), and the default Personal destination for workspaceId. This adds interpretive value beyond the schema's individual parameter notes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names the exact verb and resource: 'Saves supplied HTML as a new private Carryo website draft for review before publication.' The word 'new' and 'private...before publication' distinguishes it from siblings like website.publish and website.edit, and the title mirrors the purpose without adding noise.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description establishes clear context: this tool is for creating a private draft with no public page until published, and the Personal vs workspaceId destination is explained. It does not explicitly name alternatives such as website.edit for existing drafts or website.publish for going live, so the when-not-to-use guidance is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Carryo Website Publisher tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?