# Pagetool Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Pagetool

Draft, edit and publish a small business website from chat, then put it on your own domain.

- Record: https://musedirectory.ai/connector/pagetool
- Category: Productivity
- Developer: Pagetool (https://pagetool.io)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 388ms, checked 2026-11-17T12:36:11Z
- Endpoint: https://pagetool.io/api/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-11-17T12:36:11Z)
- Source: Found in the official MCP Registry (io.pagetool/pagetool) https://registry.modelcontextprotocol.io/v0/servers?search=io.pagetool%2Fpagetool

Connects to Pagetool's website builder and hosting. Muse can draft a full site from a brief or your own HTML, edit sections, add pages, set colors and fonts, import photos, collect form entries, check domain prices, and publish to a domain you own.

Example request: "Build me a simple site for my bakery with our hours, a menu and a contact form."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Pagetool to help me. It is a free service with an MCP server at https://pagetool.io/api/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- create_site_from_brief: BUILD FIRST, ASK LATER. Creates a complete, live draft website in one call - free, instant, no account and no sign-in. Call this as soon as someone asks for a website, using whatever you already know and sensible defaults for the rest, then show them the returned preview_url and 
- create_site_from_html: BUILD FIRST. Creates a live draft site from HTML you already have - free, instant, no account and no sign-in, fully deterministic with no language model involved. Call it immediately when the user brings you markup, then show them the returned preview_url. Choose create_site_from
- edit_section: Changes one node of a site - text, title, styling, link, image, heading level - or removes it and its descendants when remove is true. Address a section with section_id (from list_sections) or index, then aim at the node inside it with field (e.g. "heading", "body", "items[1].tit
- add_section: Adds ONE section of any kind (menu, map, faq, hours, ...) to an existing site, styled like the rest of it, without rebuilding the site. Pass content_json with that section's keys (or html with your own markup instead of kind), and position to choose where it goes (default: end, b
- add_page: Adds a new page (e.g. "/about", "/contact") to an existing site, built from html (same importer as create_site_from_html) or composed from sections/content_json in the site's own palette and fonts. Link between pages with href="/about". Respects the plan's page limit; stage:true 
- list_sections: Lists a site's top-level sections in order - each one's CURRENT index, its stable section_id, its kind, its heading, and its fields (every editable node inside it: heading, body, items[n].title, ... with each node's index and current text) - so you can aim edit_section at exactly
- list_sites: Lists every site you own, newest first - site_key, name, preview_url and when that preview link expires, whether it is published and on which domain, and when it was created and last changed. Signed in (OAuth) it lists your account; with a draft_token it lists that draft. Read-on
- archive_site: Removes one of your own UNPUBLISHED sites from your account so it no longer appears in list_sites (for example test sites). Nothing is deleted: it is the same recoverable archive the dashboard uses. Live sites, and sites with an active client pay link, are refused. Signed-in acco
- list_pages: Lists every page of a site (home first) with its path, name, draft preview URL and live URL. Use the path as the page parameter of edit_section, add_section, list_sections and the version tools. Free.
- remove_page: Removes one page (not the home page) from your site, using the dashboard's recoverable delete: a version is saved first and the page can be restored. Signed-in accounts only. Free.
- replace_page_html: Re-imports ONE page (the home page too) from new HTML, in place: same address, same share link, same place in the page order, and a version is saved first so it can be undone. Use it to refresh a page built earlier. stage:true previews it before it goes live. Free.
- prowess_buy_domain: Operator token only, during a "code prowess" build the owner authorized with a spending cap. Buys ONE domain for the business through our registrar (owner-paid; no customer charge), points it at the server and starts HTTPS. Use dry_run first to compare endings. Exact business nam
- publish_status: For a domain your site uses: does DNS point at our server, is the HTTPS certificate in place, and does the page answer? live:true means a visitor can open https://<domain> now. A fresh domain usually takes 5-15 minutes; poll every 20-30 seconds.
- record_review: Reviewer token only. Records pass or revise for one exact version of a site (from list_reviews). The operator token can publish only a version whose latest review is a pass; any edit makes a new version.
- list_reviews: For one site: whether publishing with the operator token needs a review (enforced), the current draft and staged versions (what record_review must name), and the reviews recorded so far, newest first.
- live_check: For a published domain of your site: https root 200, http and www reach https://<domain>/ in one hop, title/description/og tags name the site, og:image is a 1200x630 PNG/JPEG, the favicon is the site's own, no editor leftovers, outbound links answer, exactly one h1, no draft badg
- list_versions: Lists a site's saved versions, newest first - version_id, why it was saved, its label, whether an AI edit made it (ai: true), and when. Every edit_section and set_theme call saves the page first, so any AI edit can be undone with restore_version. Free, and no account is needed fo
- restore_version: Puts a site back to a version from list_versions - the undo button for AI edits. The current page is saved as a version first, so a restore can itself be undone. Free, and no account is needed for a draft you created.
- import_image: Copies a photo from a public URL (e.g. the business's own website) into Pagetool's image store and returns its hosted url. Use that url in content_json (hero/about/card/gallery image), in edit_section src, or in <img src> for create_site_from_html - external image URLs are otherw
- set_client_record: Saves who a site is for and where things stand: business name, contact name/email/phone, the source pages its facts came from, status (prospect, pitched, managed, declined, transferred_out) and notes. Only the fields you pass change; null clears one. list_sites shows each site's 
- create_transfer_code: Creates a one-time link that hands a managed site to a departing client: they sign in or sign up and accept, and the site (and, by default, its domain) moves to their account. The link works once and expires at expires_at; creating a new one cancels the previous one. Signed-in ac
- publish_staged: Makes a site's staged changes (edit_section/set_theme with stage: true) live. The live page is saved as a version first, so this can be undone with restore_version. Free.
- discard_staged: Drops a site's staged changes without touching the live site. Free.
- set_theme: Repaints the palette and fonts of an existing site across every section without touching its content or structure - the tool for make it warmer, darker, more corporate. At least one of palette_primary, palette_neutral, font_heading, font_body is required. Free, and no account is 
- get_preview_url: Returns the shareable preview URL for a site, plus its expiry. The create tools already return this URL, so call this only when you need it again later. Free, and no account is needed for a draft you created. You can edit or claim this draft for 7 days from creation.
- draft_create: Mints an anonymous draft identity (a draft token) with no account and no sign-in. You usually do NOT need to call this first: create_site_from_brief and create_site_from_html mint one for you and return it. Use this only when you want the token before composing anything. You can 
- export_site_html: Renders a site to a single self-contained HTML file. Paying customers only: requires a signed-in bearer token and an entitlement, so anonymous drafts do not export.
- draft_claim: Moves an anonymous draft onto the account of the signed-in user after they have authorized. Call this only once the user has said they want to keep the site - never before, and never as a precondition for building.
- domain_search: Checks availability and price for a domain, or for a bare name across a set of TLDs. Free and needs no account. Use it once the user wants their finished draft on a real address. A refused or unchecked domain ending carries `reason` and a plain `reason_text`: unsupported or price
- purchase_link: Creates the one Stripe Checkout link that pays for a domain registration and saves the card of the customer, so every later purchase can happen inside this conversation. This is the only time the user leaves the chat - give them the returned URL. Reach for this only after they ha
- purchase_execute: Charges the saved card of the customer immediately for a purchase they have explicitly agreed to in this conversation. Only call it after they have confirmed the exact item and amount in words - this tool moves real money right away. A refused or unchecked domain ending carries `
- domain_register: Completes registration for a domain the customer has ALREADY paid for. It never charges, and it never reports success it has not confirmed.
- create_client_checkout: Creates a pay link (pay_url) for a business owner with NO Pagetool account: they pay by card (US cards only) a monthly subscription (default $25/month, or price_cents) that registers the domain, keeps it renewed and puts the site live on it automatically. If they cancel, or stay 
- cancel_client_checkout: Retires a pay link that has NOT been paid (give code = the pcl_… part of pay_url, or site_key), so nobody can pay it. Nothing is charged. A link that was already paid cannot be cancelled here.
- rename_site: Changes a site's display name (shown in list_sites and the dashboard). Plain text; HTML entities like &#39; are decoded. Max 120 characters. Signed-in accounts only. Free.
- upsert_site_form: Declares a built-in form on a site you own: its fields (text, email, textarea, checkbox, month, date, tel, select), the recipient email (kept on the server, never in the page), the button label and the thank-you message. Entries are saved and emailed from Pagetool, behind Turnsti
- list_form_submissions: Lists the entries visitors sent through a site's built-in forms, newest first: the submitted fields, whether the notification email was sent, and when. Optional form_key narrows it to one form. limit defaults to 50 (max 200). No visitor IP data is returned. Test entries sent from
- site_stats: Page views and unique visitors per day for a published site, plus its top pages and the websites that sent visitors. Counted on the server with no cookies; search bots, previews and Pagetool's own checks are not counted. days defaults to 30 (max 90). Free.
- publish_site: Puts a finished site live on the domain the user has connected. publish_site takes no payment itself; it requires a signed-in account with the pagetool.sites.write scope and either an active plan or an open free trial. Everything before it - building, editing, theming, previewing
- payment_status: Read-only, truthful status of the payments and domains of the customer - use it to tell them exactly where their money and their domain stand.

Screening checks:
- MCP handshake: pass (Answered in 388ms)
- Domain against threat feeds (Cloudflare security DNS): pass (pagetool.io not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (41 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (No redirects off the domain)
- AI review of purpose and tool behavior: pass (tool descriptions push the model to build before asking, but only free drafts are created; money-moving tools require explicit item and amount confirmation)
