Create Web Page is a remote MCP server that gives an AI agent 23 tools, among them account.page.manage, account.pages.list, account.whoami. It answers at https://create-web-page.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 18 October 2026, succeeded.
Create, edit, preview, publish, and manage web pages from MCP-capable AI clients.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
account.page.manage | Read a claimed account page without requiring an editToken. Use after OAuth when the user wants to manage a durable website. Inputs: pageId |
account.pages.list | List landing pages claimed by the authenticated account. This requires OAuth and is for account management, not first-time demo creation. Inputs: limit |
account.whoami | 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 13 allowed types (link, social_row, whatsapp, phone_call, email_contact, image, gallery, video_embed, text, map_embed, product_card, lead_form, reviews) with |
block.delete | 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 For already-published pages, this saves an unpublished latest revision only.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 Inputs: pageId, editToken, blockId |
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 For already-published pages, this saves an unpublished latest revision only.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 Inputs: pageId, editToken, blockId, toIndex |
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 For already-published pages, this saves an unpublished |
layouts.list | List supported page layouts. v1 ships link_in_bio only. |
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 Inputs: pageId, editToken |
page.create | Create a hosted link-in-bio page draft from a style preset. Provide title, displayName, and a preset (or 'auto' to infer from businessType/style). The page starts with empty placeholder blocks for you to fill in via block.update — do not in Inputs: title, displayName, bio, businessType, slug, layout |
page.create_from_brief | Create a hosted landing page draft from a structured brief. Accepts business name, category, layout, palette, primary action, explicit final-audience publicSections, and optional hero image. Planning fields such as audience, offer, primaryG Inputs: businessName, bio, businessType, preferredSlug, layout, preset |
page.get | Read a landing page draft, including its latest content JSON. For anonymous demo pages, include the editToken. Inputs: pageId, editToken |
page.header.update | Update the link-in-bio page header: displayName, bio, verified checkmark, and QR display. 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 s Inputs: pageId, editToken, displayName, bio, verified, showQr |
page.intake.start | RECOMMENDED first step for building a page. Returns the few questions worth asking (business name, primary visitor action, key content, optional source link) so you can then call page.create_from_brief. This is the simplest, most reliable p Inputs: originalRequest, businessName, businessType, sourceUrl, sourceHandle, primaryGoal |
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 dr Inputs: pageId, editToken, title, slug, seoTitle, seoDescription |
page.onboarding.start | Optional planning helper that returns category/layout/palette/primary-action choices and a quality checklist (it does NOT create a page). Use it only if you want those pickers; otherwise page.intake.start → page.create_from_brief is the sim Inputs: originalRequest, locale, suggestedSelection |
page.onboarding.update | 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 al Inputs: stepId, locale, selection, knownFields |
page.preview | Return the current preview URL for a page. Inputs: pageId, editToken |
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 becaus Inputs: pageId, editToken |
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 u Inputs: pageId, editToken, theme |
page.unpublish | Remove a published landing page from public availability while keeping its draft and revision history. Inputs: pageId, editToken |
presets.list | List the 8 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.import | 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 fie Inputs: sourceUrl, locale |
Every block below points at https://create-web-page.com/mcp. Pick your client and copy.
claude mcp add --transport http create-web-page https://create-web-page.com/mcp
{
"mcpServers": {
"create-web-page": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://create-web-page.com/mcp"]
}
}
}{
"mcpServers": {
"create-web-page": {
"url": "https://create-web-page.com/mcp"
}
}
}{
"servers": {
"create-web-page": {
"type": "http",
"url": "https://create-web-page.com/mcp"
}
}
}{
"context_servers": {
"create-web-page": {
"url": "https://create-web-page.com/mcp"
}
}
}{
"mcpServers": {
"create-web-page": {
"serverUrl": "https://create-web-page.com/mcp"
}
}
}{
"mcpServers": {
"create-web-page": {
"url": "https://create-web-page.com/mcp"
}
}
}name: Create Web Page
version: 0.0.1
schema: v1
mcpServers:
- name: Create Web Page
type: streamable-http
url: https://create-web-page.com/mcp{
"mcpServers": {
"create-web-page": {
"httpUrl": "https://create-web-page.com/mcp"
}
}
}{
"mcpServers": {
"create-web-page": {
"type": "http",
"url": "https://create-web-page.com/mcp"
}
}
}{
"mcpServers": {
"create-web-page": {
"url": "https://create-web-page.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fcreate-web-page.com%2Fmcp&type=streamable_http&id=create-web-page&name=Create%20Web%20Page
It answered our last check on 18 October 2026 in 228 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by create-web-page.com and served from create-web-page.com, the vendor's own domain: https://create-web-page.com/mcp.
23, as returned by the server's own tools/list on 10 September 2026: account.page.manage, account.pages.list, account.whoami, block.add, block.delete, block.reorder, block.update, layouts.list, and 15 more.
It answered our last check on 18 October 2026 in 228 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://create-web-page.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.create-web-page. Endpoint host: create-web-page.com. ARD identifier: urn:air:com.create-web-page:mcp:create-web-page.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.