Summary
Lets Claude build complete WebCake landing pages from plain language prompts by exposing the full element catalog, JSON schema, and validation rules. It knows the exact structure of every WebCake component (hero, form, countdown, product list, cart) and guides the AI to assemble valid page JSON with absolute positioning, CTAs, and form fields. The validate_page tool catches layout errors before persistence, and the create_page and patch_page tools push directly to your WebCake account with dry-run previews. You describe the page you want, the AI calls list_elements and get_generation_guide to learn the model, builds the JSON, validates it, and saves it. You get an editable page in the WebCake editor without touching the schema yourself. Works over stdio locally or as a hosted endpoint with JWT auth.
Install to Claude Code
verifiedclaude mcp add --transport http webcake-landing-mcp https://mcp.toolvn.io.vn/mcp --header 'Authorization: YOUR_AUTHORIZATION'Run in your terminal. Add --scope user to make it available in every project.
Review the command, arguments, and environment values before installing — MCP servers run with your local permissions.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Tools
Verified live against the running server on Jun 10, 2026.
verified live19 tools
get_generation_guideReturns the page-building conventions reference: output shape, the absolute-positioning coordinate system, event vocabulary, and the recommended workflow.
Returns the page-building conventions reference: output shape, the absolute-positioning coordinate system, event vocabulary, and the recommended workflow.
No parameters — call it with no arguments.
list_elementsList every supported element type, grouped by category, with a one-line summary and whether it is a container (can hold children).
List every supported element type, grouped by category, with a one-line summary and whether it is a container (can hold children).
No parameters — call it with no arguments.
get_elementReturns detailed usage for one element type — or for many in a single call (BATCH MODE): summary, when to use it, key `specials` fields, a SPARSE skeleton node (the exact shape to emit — the server hydrates omitted boilerplate), and (for common types) a filled example. Pass `t...2 params
Returns detailed usage for one element type — or for many in a single call (BATCH MODE): summary, when to use it, key `specials` fields, a SPARSE skeleton node (the exact shape to emit — the server hydrates omitted boilerplate), and (for common types) a filled example. Pass `t...
Parameters* required
typestringSingle element type — backward-compat. Prefer `types` when fetching more than one.
typesarrayMultiple element types to fetch in one call (recommended for a section that needs several types, e.g. ['section','text-block','button','form','input']).
get_page_schemaReturns the full JSON Schema (Draft 2020-12) of a Webcake page source object { page: [...], settings: {...} } for structural reference and validation.
Returns the full JSON Schema (Draft 2020-12) of a Webcake page source object { page: [...], settings: {...} } for structural reference and validation.
No parameters — call it with no arguments.
new_elementReturns a default element node for a type in the SPARSE authoring shape (fresh id, both breakpoints' seeded styles, seeded specials). Emit elements exactly like this — fill in specials + top/left coordinates; OMIT properties/runtime/empty events/config (the server hydrates the...2 params
Returns a default element node for a type in the SPARSE authoring shape (fresh id, both breakpoints' seeded styles, seeded specials). Emit elements exactly like this — fill in specials + top/left coordinates; OMIT properties/runtime/empty events/config (the server hydrates the...
Parameters* required
namestringOptional properties.name override (layer label).
type*stringElement type to create.
new_page_skeletonReturns an empty but complete top-level page source { page:[], popup:[], settings:{...defaults}, options:{...}, cartConfigs:{} } matching the real editor shape.1 params
Returns an empty but complete top-level page source { page:[], popup:[], settings:{...defaults}, options:{...}, cartConfigs:{} } matching the real editor shape.
Parameters* required
mobileOnlybooleantrue if the page renders mobile-only.
validate_pageValidates a page source against the schema + semantic rules (unique ids, dangling event targets, children only on containers, missing field_name, top-level types) plus form-data bindings (duplicate field_name within one form, dangling option-event promoId / connectedSurvey / c...1 params
Validates a page source against the schema + semantic rules (unique ids, dangling event targets, children only on containers, missing field_name, top-level types) plus form-data bindings (duplicate field_name within one form, dangling option-event promoId / connectedSurvey / c...
Parameters* required
pagevalueThe page source object { page:[...], settings:{} } OR a JSON string of it.
search_imagesSearches Pexels stock photos (see https://www.pexels.com/api/) by short English subject queries. Returns hotlinkable URLs at several sizes (src.large for heroes/banners, src.medium for cards/thumbs), `avg_color` for matching section backgrounds, plus photographer name and attr...8 params
Searches Pexels stock photos (see https://www.pexels.com/api/) by short English subject queries. Returns hotlinkable URLs at several sizes (src.large for heroes/banners, src.medium for cards/thumbs), `avg_color` for matching section backgrounds, plus photographer name and attr...
Parameters* required
pageintegerResult page for pagination (default 1).
pickstringWith `queries`, 'best' (default) returns only the top photo per query (compact, drop-in for specials.src); 'all' returns the full result. Single-query calls always return the full result.one of
best · allsizestringMinimum photo size to return (default any).one of
large · medium · smallcolorstringOptional color filter: a name (red, blue, …) or a hex like '6a8f3c'.
querystringSingle subject query — backward-compat. Prefer `queries` when the page needs 2+ images.
queriesarrayMultiple subject queries (one per image slot) to run in parallel — recommended for a page with 2+ images so each only costs ONE round-trip.
per_pageintegerPhotos per query (default 5).
orientationstringPreferred shape — 'landscape' for heroes/banners, 'portrait' for tall cards, 'square' for icons/avatars.one of
landscape · portrait · squareingest_htmlParses an HTML string into a compact reference AST: title, description, og_image, language, and an array of sections classified by role (header, hero, features, about, form, cta, gallery, testimonials, pricing, faq, footer, unknown) with headings, subheadings, paragraphs, imag...2 params
Parses an HTML string into a compact reference AST: title, description, og_image, language, and an array of sections classified by role (header, hero, features, about, form, cta, gallery, testimonials, pricing, faq, footer, unknown) with headings, subheadings, paragraphs, imag...
Parameters* required
html*stringRaw HTML of a page or a section.
intentstringHow the caller intends to use the result. 'adapt' (default) — use as a layout reference and rewrite content for the user's brand. 'clone' — keep text and images close to the original.one of
adapt · cloneingest_urlFetches a public webpage (GET, 10s timeout, 2MB cap) and parses it into the same compact reference AST as ingest_html. Returns a warning when the page appears client-rendered (empty <body>) so the caller can fall back to a screenshot — Claude can analyze a screenshot natively...2 params
Fetches a public webpage (GET, 10s timeout, 2MB cap) and parses it into the same compact reference AST as ingest_html. Returns a warning when the page appears client-rendered (empty <body>) so the caller can fall back to a screenshot — Claude can analyze a screenshot natively...
Parameters* required
url*stringPublic HTTP(S) URL of the page to fetch.
intentstringHow the caller intends to use the result. 'adapt' (default) — use as a layout reference and rewrite content for the user's brand. 'clone' — keep text and images close to the original.one of
adapt · clonelist_organizationsReturns the account's Webcake organizations (id, name, is_default). The default org (type===1, usually the personal workspace) is where pages normally go. Needs WEBCAKE_API_BASE + WEBCAKE_JWT.
Returns the account's Webcake organizations (id, name, is_default). The default org (type===1, usually the personal workspace) is where pages normally go. Needs WEBCAKE_API_BASE + WEBCAKE_JWT.
No parameters — call it with no arguments.
create_pagePersists a page source to the configured Webcake backend: creates a NEW page and saves the source (source-only — opens in the editor where re-saving renders it). Validates first. DEFAULTS to dry_run=true (validates, caches the source as draft_id, returns the HTTP request it WO...5 params
Persists a page source to the configured Webcake backend: creates a NEW page and saves the source (source-only — opens in the editor where re-saving renders it). Validates first. DEFAULTS to dry_run=true (validates, caches the source as draft_id, returns the HTTP request it WO...
Parameters* required
namestringPage name (default 'AI Page').
sourcevaluePage source { page, popup, settings, options, cartConfigs } (object or JSON string). Required unless draft_id is given. Author elements SPARSE — only id, type, responsive.<bp>.styles for BOTH breakpoints, specials, and real events; OMIT properties/runtime/empty events+children/per-breakpoint config — the server hydrates them from factory defaults (a full node also works).
dry_runbooleanDefault TRUE — validate, cache the source as draft_id, and preview the request without sending. Set false to actually create.
draft_idstringA draft_id from a previous create_page call (validation failure, dry_run=true, or a timed-out/failed create). Loads the cached source — no need to re-send the full JSON. Use for dry-run → real call transitions, fix-after-error rounds, and retrying after a timeout.
organization_idstring | numberOrganization to create the page in (from list_organizations). Omit for a personal page; falls back to WEBCAKE_ORG_ID env if set.
list_pagesLists the pages owned by the account (id, name, organization_id, updated_at), most-recent first. Needs WEBCAKE_API_BASE + WEBCAKE_JWT.
Lists the pages owned by the account (id, name, organization_id, updated_at), most-recent first. Needs WEBCAKE_API_BASE + WEBCAKE_JWT.
No parameters — call it with no arguments.
find_pagesSearches the account's pages by name, domain, and/or page id so you can locate the page to edit, then pass its id to get_page → update_page/add_section. Filters are AND-combined (e.g. name='sale' + domain='shop.com'). Each result includes id, name, organization_id, custom_doma...4 params
Searches the account's pages by name, domain, and/or page id so you can locate the page to edit, then pass its id to get_page → update_page/add_section. Filters are AND-combined (e.g. name='sale' + domain='shop.com'). Each result includes id, name, organization_id, custom_doma...
Parameters* required
namestringCase-insensitive substring of the page name to match.
limitintegerMax results (default 50, capped at 100).
domainstringCase-insensitive substring of the page's domain (matches custom_domain OR default_domain).
page_idstringExact page id — narrows to that single page (useful to confirm it exists/owned).
get_pageFetches an existing page's decoded source tree { page, popup, settings, options, cartConfigs } plus name and organization_id. By DEFAULT the source is COMPACTED: boilerplate every element shares (properties/runtime/empty events+children/per-breakpoint config + factory-default...2 params
Fetches an existing page's decoded source tree { page, popup, settings, options, cartConfigs } plus name and organization_id. By DEFAULT the source is COMPACTED: boilerplate every element shares (properties/runtime/empty events+children/per-breakpoint config + factory-default...
Parameters* required
compactbooleanDefault TRUE — strip factory-default boilerplate from every element (sparse shape, far fewer tokens). false returns the raw stored tree.
page_id*stringThe page id (from list_pages or a URL).
update_pageOverwrites an EXISTING page's source with an edited tree (source-only; re-render in the editor for preview/publish). Validates first. DEFAULTS to dry_run=true (validates, caches the source as draft_id, previews the request, token masked); dry_run=false to actually save. Accept...4 params
Overwrites an EXISTING page's source with an edited tree (source-only; re-render in the editor for preview/publish). Validates first. DEFAULTS to dry_run=true (validates, caches the source as draft_id, previews the request, token masked); dry_run=false to actually save. Accept...
Parameters* required
sourcevalueThe edited page source { page, popup, settings, options, cartConfigs } (object or JSON string). Required unless draft_id is given. The compacted tree from get_page can be edited and sent back AS-IS — sparse nodes are re-hydrated from factory defaults (a full tree also works).
dry_runbooleanDefault TRUE — validate, cache the source as draft_id, and preview without sending. Set false to actually save.
page_idstringThe page id to update (must be owned by the account). Required unless draft_id is given (the page_id is stored in the draft).
draft_idstringA draft_id from a previous update_page call (dry_run=true or a timed-out/failed update). Loads the cached source — no need to re-send the full JSON. Use for dry-run → real call transitions and retrying after a timeout.
add_sectionAppends one or more SECTIONS to an existing page WITHOUT re-sending the whole source — the incremental-build path that avoids large create_page payloads. The backend appends section(s) to the END of `page` server-side and rejects duplicate element ids, so the caller sends only...4 params
Appends one or more SECTIONS to an existing page WITHOUT re-sending the whole source — the incremental-build path that avoids large create_page payloads. The backend appends section(s) to the END of `page` server-side and rejects duplicate element ids, so the caller sends only...
Parameters* required
dry_runbooleanDefault TRUE — validate the section(s) and preview the request without writing. Set false to actually append.
page_id*stringThe page id to append to (from create_page or list_pages; must be owned by the account).
draft_idstringA draft id returned by a previous add_section call (dry_run=true or validation failure). Loads the cached section payload — no need to re-send the sections JSON. Use for dry-run → real call transitions and fix-after-error rounds.
sectionsvalueOne section node, or an array of section nodes, to append to the END of `page` (object/array or JSON string). Each is a normal section element { id, type:'section', responsive, children, … } with a UNIQUE id; they stack vertically after the existing sections. Author SPARSE nodes — omit properties/runtime/empty events+children/per-breakpoint config; the server hydrates them from factory defaults. Required unless draft_id is supplied.
patch_pageEdits a page by element id WITHOUT re-sending the whole source — the surgical-edit and fix-after-error path. Targets EITHER a live page (page_id) OR a cached draft source (draft_id). Draft sources come from: (a) create_page — failed validation or timed-out network call → patch...4 params
Edits a page by element id WITHOUT re-sending the whole source — the surgical-edit and fix-after-error path. Targets EITHER a live page (page_id) OR a cached draft source (draft_id). Draft sources come from: (a) create_page — failed validation or timed-out network call → patch...
Parameters* required
dry_runbooleanDefault TRUE — load, merge, validate and preview the resulting save WITHOUT writing. Set false to actually save.
page_idstringEdit a LIVE page by id (from create_page, list_pages, or find_pages; must be owned by the account). Provide page_id OR draft_id. For a sections or update draft_id you may also pass page_id here to override the stored page target.
patchesvalueOne op object or an array of them (object/array or JSON string). Each targets an element by id: {op:'update',id,type?,specials?,styles?:{desktop?,mobile?},config?:{desktop?,mobile?},events?,properties?} merges fields into the element (op may be omitted; set `type` to fix a wrong element type); {op:'replace',id,element} swaps the node; {op:'remove',id} deletes it; {op:'add',parent_id,element} appends a child to a container. `element` may be a SPARSE node (id/type/styles/specials/events only) — the server hydrates omitted boilerplate from factory defaults. OMIT (or pass empty array) when draft_id is given and you just want to commit/retry the cached draft as-is.
draft_idstringCommit or fix a CACHED source: from create_page (failed/timed-out → new page created once valid), add_section (dry_run or failure → sections appended), or update_page/live-page patch (timed-out/failed → updatePageSource retried). The originating tool's error/dry_run response returns draft_id. Provide page_id OR draft_id. Empty/omitted patches = commit the cached draft as-is (the RETRY PATH after a timeout).
publish_pagePublishes an EXISTING page: saves the stored source as a new version and creates/updates its page_published record (live status), optionally attaching a custom domain/path. NOT needed for the preview link — /preview/<page_id> on the preview host renders the stored source direc...4 params
Publishes an EXISTING page: saves the stored source as a new version and creates/updates its page_published record (live status), optionally attaching a custom domain/path. NOT needed for the preview link — /preview/<page_id> on the preview host renders the stored source direc...
Parameters* required
dry_runbooleanDefault TRUE — preview the request without sending. Set false to actually publish.
page_id*stringThe page id to publish (must be owned by the account).
custom_pathstringOptional path under the custom domain (e.g. 'sale').
custom_domainstringOptional custom domain to serve the page at (e.g. 'shop.example.com' — must already point at Webcake). Omit to publish without a domain (served at the preview-host URL).
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Configuration
WEBCAKE_JWTsecretWebcake backend JWT; required only for the persistence tools (create/update/list pages).
WEBCAKE_ENVWebcake environment preset that fills the API/app/builder base URLs.
WEBCAKE_API_BASEOverride for the Webcake API base URL (takes precedence over WEBCAKE_ENV).
WEBCAKE_ORG_IDDefault Webcake organization id for the persistence tools.
PEXELS_API_KEYsecretOptional Pexels API key for search_images; without one a shared hosted proxy is used.
Categories
Registryactive
Packagewebcake-landing-mcp
TransportSTDIO, HTTP
AuthRequired
Tools verifiedJun 10, 2026
UpdatedJun 10, 2026
WebCake Landing MCP
