Search / com.create-web-page/create-web-page
protogridR0· no sign-inCreate, edit, preview, publish, and manage web pages from MCP-capable AI clients.
v0.1.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"create-web-page": {
"type": "http",
"url": "https://create-web-page.com/mcp"
}
}
}claude mcp add --transport http create-web-page https://create-web-page.com/mcp[mcp_servers.create-web-page]
url = "https://create-web-page.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"create-web-page": {
"type": "remote",
"url": "https://create-web-page.com/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"create-web-page": {
"type": "http",
"url": "https://create-web-page.com/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=create-web-page&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vY3JlYXRlLXdlYi1wYWdlLmNvbS9tY3AifQ%3D%3D"
}{
"servers": {
"create-web-page": {
"type": "http",
"url": "https://create-web-page.com/mcp"
}
}
}{
"mcpServers": {
"create-web-page": {
"httpUrl": "https://create-web-page.com/mcp"
}
}
}extensions:
"create-web-page":
enabled: true
name: "create-web-page"
type: streamable_http
uri: "https://create-web-page.com/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_length1 tools have descriptions over 1,024 characters, which crowds the contexttools.schemasevery tool has an object input schematools.annotations27 of 27 tools declare readOnlyHint or destructiveHinttools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHinttools.token_costabout 16,996 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes46 tool changes in 30 daysstability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting themdeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageblock_reorderchangedoutput schemablock_deletechangedoutput schemablock_updatechangedoutput schemapage_unpublishchangedoutput schemapage_publishchangedoutput schemapage_previewchangedoutput schemapage_meta_updatechangedoutput schemapage_theme_updatechangedoutput schemapage_header_updatechangeddescription, input schema, output schemaUpdate the link-in-bio page header: displayName, bio, verified checkmark, QR display, business-card display style ("photo_hero" large top photo or "avatar"), a short role label (e.g. "Barber · Madrid"), labelPosition, and the header photo (photoUrl; null removes it). Use only the fields you want to change. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down.
Update the link-in-bio page header: displayName, bio, verified checkmark, business-card display style ("photo_hero" large top photo or "avatar"), a short role label (e.g. "Barber · Madrid"), labelPosition, and the header photo (photoUrl; null removes it). Use only the fields you want to change. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down.
account_page_managechangedoutput schemaShowing the latest 10. Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace +website +reachable +uptime-100% ~updated-145d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://create-web-page.com/mcp streamable-http | none | yes | 100% | 224 ms | 2025-06-18 | 2026-10-19 |
account_page_manageread-only | Read a claimed account page without requiring an editToken. Use after OAuth when the user wants to manage a durable website. |
account_pages_listread-only | List landing pages saved to the signed-in account. Safe to call without sign-in: an anonymous chat gets ok=true, authenticated=false and an empty list (not an error) because it has no saved pages — then create the page directly with page_create_from_brief. Sign-in is only needed later to keep or manage a page. |
account_whoamiread-only | Return the current Create Web Page account context. Use this to check whether the user is authenticated or using an anonymous expiring demo. |
block_add | Append a new content block to a link-in-bio page. The block must match one of the 14 allowed types (link, social_row, whatsapp, phone_call, email_contact, image, gallery, video_embed, text, map_embed, product_card, lead_form, reviews, save_contact) with that type's strict props. The server generates the block id and returns it in the response. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. The response includes nextSteps: after adding a block, share these hints with the user so they know what else would make the page more complete. |
block_deletedestructive | Delete one block by stable blockId. Use page_get first if unsure which id to remove. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. |
block_reorder | Move a block to a new zero-based index in the page main slot. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. |
block_update | Patch one content block by stable blockId. Provide a props patch (merged into existing props) and/or a new type. Block types and props are validated against the strict per-type schema. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. |
layouts_listread-only | List supported page layouts. Currently ships link_in_bio only. |
media_attach | Attach a ready media asset to the page. placement determines where: avatar (header), block_image (image inside a specific block — requires blockId), gallery_item (appended to a gallery — optional blockId targets a specific gallery; otherwise the first one is used), background (theme background). |
media_deletedestructive | Soft-delete a media asset and remove all references to it from the page content. |
media_upload | Add an image to a page. PREFERRED for any image already on the web: pass its imageUrl and the server fetches it directly (no size limit, no attachment needed in chat). imageBase64 is ONLY for very small inline images — large base64 payloads are rejected by request-size limits and waste context, so never paste a photo's bytes; for a file on the user's device use media_upload_link_create instead. After a successful upload, call media_attach to place it (unless this returned content already showing it). |
media_upload_link_create | Get an upload link for a photo on the user's own device (phone/computer) — the right tool whenever the image is not already at a public URL. Pass pageId (+ editToken for demo pages) and the placement (e.g. header_photo). Then show the returned uploadPageUrl to the user as a clickable link and ask them to open it and pick their photo: the page resizes the image for the web automatically and attaches it to the page, so you do NOT call media_attach afterward. The link expires (see expiresAt). After the user says they've uploaded, call page_get to confirm the photo is on the page. |
page_claim | Claim an anonymous demo page into an AUTHENTICATED account. This requires the signed-in user's OAuth — an anonymous chat/agent session cannot call it and will get an OAuth-required error. So in a normal agent conversation, do NOT call this to 'save' a demo page: instead share the claimUrl from the page_create/page_publish result with the user, who opens it, signs in, and keeps the page. Only call page_claim when the request already runs under the owner's OAuth. |
page_create | Low-level/legacy: create a blank link-in-bio scaffold from a style preset (title, displayName, preset or 'auto'). Not for normal page requests — use page_create_from_brief, which builds the page from the user's details. The scaffold starts with empty placeholder blocks to fill via block_update — do not invent content. This tool intentionally creates a draft only and does not return a publish action. After calling it, stop and show the preview URL. Do not call page_publish in the same turn unless the user's current message explicitly asks to publish, make the page live, or get a public share link. Anonymous demo pages expire unless claimed. |
page_create_from_brief | The main tool for creating a page. Call it directly when the request already has the business/page name and the main visitor action with its real destination (WhatsApp number with country code, booking/order link, phone, address or email); if the request is vague, ask at most one round of questions first (page_intake_start lists them). Creates a private draft and returns previewUrl, pageId, editToken (anonymous pages), claimUrl and expiresAt. Planning fields (audience, offer, primaryGoal, location, businessType, style, mustInclude) are context only and are not rendered as public body copy. Draft previews are customer-facing: do not pass owner instructions, section-planning labels, or placeholder copy as public content. Keep sparse briefs sparse: use only facts supplied by the user or imported public sources, plus light wording polish; never invent menus, services, hours, facilities, locations, testimonials, guarantees, staff details, prices, or operational claims. If a requested action lacks its real destination, ask for it, or use fallbackLeadForm with destinationEmail (ask the user which email should receive enquiries — without it the form cannot deliver anything and cannot be the page's only action at publish). Personal, gift or event pages (birthday, invitation, tribute, a poem) need no contact form and no action at all: a page with real text (bio + publicSections) can be published as is; add a link (primaryActionUrl, e.g. RSVP, gift list or playlist) only if the user has one, never primaryActionId 'lead'. After calling it, show the preview URL and stop; call page_publish only when the user explicitly asks to publish, make it live, or get a public link. Anonymous pages are deleted after expiresAt unless the user claims them via claimUrl. Passing onboardingMainCategory picks the matching template. The draft also seeds the preset's starter blocks (empty placeholder links, social row, save-contact) — they never block publishing and are pruned if left empty. Use the returned previewUrl directly (no need for page_preview). nextSteps marked recommended/optional (bio, photo, social links) are improvements to offer after the user has seen the preview; only 'required' ones block publishing. |
page_getread-only | Read a landing page draft, including its latest content JSON. For anonymous demo pages, include the editToken. |
page_header_update | Update the link-in-bio page header: displayName, bio, verified checkmark, business-card display style ("photo_hero" large top photo or "avatar"), a short role label (e.g. "Barber · Madrid"), labelPosition, and the header photo (photoUrl; null removes it). Use only the fields you want to change. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. |
page_intake_startread-only | Optional first step for a vague page request (e.g. 'make me a website for my barbershop'). Returns at most one round of questions to ask together: the name, the main visitor action AND where it goes (WhatsApp number with country code, booking/order link, phone or address), and must-have facts. Skip it when the request already has a name and the main action's destination — call page_create_from_brief directly. Call at most once per request; if the user gave a public link, read it yourself or use source_import instead. Does not create a page. |
page_meta_update | Update internal page title, URL slug, and SEO title/description. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. |
page_onboarding_startread-only | Guided visual setup (category, layout, palette, primary action) that does NOT create a page. Use it ONLY when the user explicitly wants to choose the style/layout step by step; for normal requests call page_create_from_brief (asking at most one round of questions first). IMPORTANT: this flow is STATELESS — page_onboarding_update does not remember earlier calls, so each update must resend the FULL set of selections + knownFields gathered so far. As soon as you have a business name and a primary action, stop and call page_create_from_brief (you do not need to reach a 'ready' step). |
page_onboarding_updateread-only | Validate onboarding selections and return the remaining checklist. STATELESS: it does not remember previous calls, so every call must include the FULL accumulated selection (mainCategory, subCategory, layout, palette, primaryAction) plus all knownFields (name, description, action destination, etc.) gathered so far — not just the latest answer, or earlier choices will look 'missing'. You do not need to loop to a 'ready' state: once you have a name and a primary action, call page_create_from_brief with those values. |
page_previewread-only | Return the current preview URL for a page. You usually do not need this: page_create and page_create_from_brief already return a ready-to-open previewUrl. For an anonymous demo page you must pass the editToken from the create result; calling this with pageId alone fails. |
page_publish | Publish the latest page revision. Call this only when the user's latest message explicitly asks to publish, make the page live, or get a public share link. Do not call this immediately after page_create or page_create_from_brief just because the draft is publish-ready. For anonymous demo pages, include the editToken returned by page_create. The response includes nextSteps: always share these with the user after publishing — they include the claim reminder and any remaining improvements. |
page_theme_update | Apply a partial theme patch. Theme fields are enum-constrained (button variant/radius/shadow, font family/weight, density, icon_size). Use presets_list first if the user wants a complete restyle. For already-published pages, this saves an unpublished latest revision only. Do not call page_publish in the same assistant turn after this edit. Stop and tell the user the draft/preview was updated, then wait for a separate user message that explicitly asks to update the live link, publish, or make the changes public before calling page_publish. Do NOT call page_unpublish either — the live page should stay public; only unpublish when the user explicitly asks to take it down. |
page_unpublishdestructive | Remove a published landing page from public availability while keeping its draft and revision history. |
presets_listread-only | List the 12 curated style presets (theme + starter blocks) for link-in-bio. Use to offer the user a choice or to confirm a preset:auto selection. |
source_importread-only | Fetch a public website URL and extract a structured brief with business name, description, contact links, and suggested page blocks. Only works with public HTTP/HTTPS pages. Does not bypass login, CAPTCHA, or paywalls. Returns extracted fields and suggestedBlocks for use with page_create_from_brief. |
Schemas: list_tools.
{
"name": "com.create-web-page/create-web-page",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"canonicalUtm": "https://create-web-page.com?utm_source=mcp_registry&utm_medium=directory",
"distributionPlan": "https://create-web-page.com/docs/mcp"
}
},
"icons": [
{
"src": "https://create-web-page.com/brand/raster/app-icon-dark-1024.png",
"sizes": [
"1024x1024"
],
"theme": "dark",
"mimeType": "image/png"
},
{
"src": "https://create-web-page.com/brand/raster/app-icon-light-1024.png",
"sizes": [
"1024x1024"
],
"theme": "light",
"mimeType": "image/png"
}
],
"title": "Create Web Page",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://create-web-page.com/mcp",
"type": "streamable-http"
}
],
"version": "0.1.0",
"repository": {
"url": "https://github.com/daniel-lopez-puig/landings",
"source": "github"
},
"websiteUrl": "https://create-web-page.com/docs/mcp",
"description": "Create, edit, preview, publish, and manage web pages from MCP-capable AI clients."
}