Skip to content

MCP servers › io.pagetool › pagetool

MCP server · registry snapshot 2026-11-18 · last tested 2026-11-18

pagetool MCP server

Registry name io.pagetool/pagetool

by pagetool.io · domain (the registry's namespace rule)Website ↗

Build and host websites from a chat: draft free, edit and theme, then publish to your own domain. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-18version 1.1.0streamable HTTP41 tools

Summary

io.pagetool/pagetool is a remote MCP server listed in the official MCP registry at version 1.1.0, under the namespace of the domain pagetool.io. On 2026-11-18 ProtocolProbe connected to it in read-only mode and read its inventory: 41 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Tools
41
Last tested
2026-11-18

Tool list size

19,116 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (41 tools). Counted with Anthropic's token counter on 2026-11-18, from the tool list we read on 2026-11-18. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-18 (pagetool.io), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.1.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 19 tools whose name or declaration suggests they change data (create_site_from_brief, create_site_from_html, edit_section, add_section, add_page and 14 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-18.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-18
Mode
read-only (no tool calls)
Latest version
1.1.0, published 2026-11-17 (registry, as of the 2026-11-18 snapshot)
First listed version
2026-11-17 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-11-18
Package and repository
checked 2026-11-18
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-17, listed on 2026-11-18 with version 1.1.0 (published 2026-11-17).

Source: the official MCP Registry list on 2026-11-17 and on 2026-11-18.

What it is

What does this server offer?

Observed inventory
41tools
0resources
0prompts

None of its 41 tools are described as changing anything. For 41 the reading was uncertain, so no mark is shown.

  • create_site_from_brief

    “BUILD FIRST, ASK LATER.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    14 inputs, 1 required
    • business_namestringrequired“The business or site name.”
    • templatestring“Optional starter template - the same ones people pick in the editor.”
    • taglinestring“Short tagline/subheading, max 200 chars.”
    • sectionsstring“Comma-separated section kinds to include, in order, e.g.”
    • contact_emailstring“Contact email shown in the contact section, if included.”
    • contact_phonestring“Contact phone shown in the contact section, if included.”
    • contact_addressstring“Contact address shown in the contact section, if included.”
    • palette_primarystring“Primary brand colour as a #rrggbb hex string.”
    • palette_neutralstring“Neutral text/background colour as a #rrggbb hex string.”
    • font_headingstring“Heading font family name.”
    • font_bodystring“Body font family name.”
    • content_jsonstring or object“Per-section content, keyed by section kind (the kind must also be in sections), as a JSON string or an object, max 64KB.”
    • site_namestring“Optional display name for the site row (defaults to business_name).”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • create_site_from_html

    “BUILD FIRST.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    4 inputs
    • htmlstring“The raw HTML to import.”
    • pagesarray“Build a whole site in one call instead of html: a list of up to 10 pages, each { path, html, name?”
    • site_namestring“Optional display name for the site (defaults to the document title, or "Imported site").”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • edit_sectionon 2 other servers

    “Changes one node of a site - text, title, styling, link, image, heading level - or removes it and its descendants when remove is true.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    18 inputs
    • pagestring“Which page of the site, as its path ("/about", "/contact").”
    • site_keystring“The site to edit.”
    • indexinteger“The section (or node) index to edit or remove.”
    • section_idstring“The stable id of the section to address, exactly as list_sections returns it (e.g.”
    • fieldstring“Which node inside the addressed section to change, from that section's fields in list_sections: "heading", "body", "text[n]", "links[n]", "image", "items[n].ti…”
    • removeboolean“When true, removes this section and its descendants instead of editing it (with field "items[n]": removes that one card).”
    • add_itemobject“Adds one card to the addressed section (services, features, pricing, products, testimonials...), styled like its last card.”
    • contentstring“New text content for this section.”
    • titlestring“New title attribute for this section.”
    • class_namestring“New Tailwind class string for this section.”
    • hrefstring“New link target (http:, https:, mailto:, tel:, a path starting with /, or an in-page anchor like #pricing).”
    • srcstring“New image/media source (same URL scheme rules as href).”
    • altstring“New alt text for an image section.”
    • html_idstring“New HTML id for the node (e.g.”
    • subtypestring“New subtype for this section.”
    • levelinteger“New heading level (1-6) when this section is a heading textBox.”
    • stageboolean“true = work on a staged copy instead of the live site: preview it at staged_preview_url, then publish_staged or discard_staged.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • “Adds ONE section of any kind (menu, map, faq, hours, ...) to an existing site, styled like the rest of it, without rebuilding the site.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    9 inputs
    • pagestring“Which page of the site, as its path ("/about", "/contact").”
    • site_keystring“The site to add to.”
    • kindstring“The kind of section to add: hero, about, services, features, gallery, testimonials, pricing, faq, hours, contact, cta, footer, menu, map, social, header, produ…”
    • content_jsonstring or object“This section's content, as a JSON string or an object, with the same keys as create_site_from_brief's content_json uses for this kind (e.g.”
    • positioninteger“0-based slot among the top-level sections (indexes as in list_sections order).”
    • htmlstring“Instead of kind: your own markup for the new section(s), e.g.”
    • colorsobject“Optional, for kind "map" only.”
    • stageboolean“true = work on a staged copy instead of the live site: preview it at staged_preview_url, then publish_staged or discard_staged.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • “Adds a new page (e.g.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    8 inputs, 1 required
    • site_keystring“The site to add a page to.”
    • pathstringrequired“The new page's path, e.g.”
    • namestring“The page name shown in the editor's page list.”
    • htmlstring“Build the page from this HTML (same importer as create_site_from_html).”
    • sectionsstring“Comma-separated section kinds to compose the page from when html is omitted: hero, about, services, features, gallery, testimonials, pricing, faq, hours, conta…”
    • content_jsonstring or object“Per-section content keyed by section kind, exactly as create_site_from_brief's content_json.”
    • stageboolean“true = work on a staged copy instead of the live site: preview it at staged_preview_url, then publish_staged or discard_staged.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • list_sectionson 31 other servers

    “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, ...”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    4 inputs
    • pagestring“Which page of the site, as its path ("/about", "/contact").”
    • site_keystring“The site to list.”
    • stageboolean“true = work on a staged copy instead of the live site: preview it at staged_preview_url, then publish_staged or discard_staged.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • “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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • archive_site

    “Removes one of your own UNPUBLISHED sites from your account so it no longer appears in list_sites (for example test sites).”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world no

    1 input, 1 required
    • site_keystringrequired“The site to archive.”
  • “Lists every page of a site (home first) with its path, name, draft preview URL and live URL.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • site_keystring“The site whose pages to list.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • “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.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world no

    2 inputs, 2 required
    • site_keystringrequired“The site to remove a page from.”
    • pathstringrequired“The page to remove, e.g.”
  • 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.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world no

    6 inputs, 1 required
    • site_keystring“The site the page belongs to.”
    • pathstring“The page to replace, e.g.”
    • htmlstringrequired“The new full HTML for this page, imported exactly like create_site_from_html (the result includes the import report).”
    • stageboolean“true = replace a staged copy instead of the live page: preview it at staged_preview_url, then publish_staged or discard_staged.”
    • keep_added_sectionsboolean“true = keep the sections added with add_section (reviews, map and the like) after the imported content, in their original order.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • prowess_buy_domain

    “Operator token only, during a "code prowess" build the owner authorized with a spending cap.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    3 inputs, 1 required
    • domainstringrequired“The ONE domain to buy for this business, bare, e.g.”
    • site_keystring“The site this domain is for (optional; for your own bookkeeping).”
    • dry_runboolean“true = quote only: registrar, cost for the minimum term, and whether it fits the cap.”
Show 29 more tools
  • publish_statuson 1 other server

    “For a domain your site uses: does DNS point at our server, is the HTTPS certificate in place, and does the page answer?”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • domainstringrequired“The domain to check, e.g.”
  • record_reviewon 1 other server

    “Reviewer token only.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    5 inputs, 3 required
    • site_keystringrequired“The site you reviewed.”
    • versionstringrequired“The exact version you reviewed: current_draft_version (before publish_site) or current_staged_version (before publish_staged) from list_reviews.”
    • verdictstringrequired“pass lets the operator publish this exact version; revise blocks it until a new version passes.”
    • itemsarray“What must change (up to 50 short items).”
    • notestring“Optional summary of the review (up to 2000 characters).”
  • “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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • site_keystringrequired“The site whose reviews and current reviewable versions to list.”
  • 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…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    3 inputs, 1 required
    • domainstringrequired“The published domain to check, e.g.”
    • namestring“The person or business the title and og tags must name.”
    • storedboolean“true = return the newest stored report (including the automatic one ~2 minutes after publish_site) without fetching.”
  • list_versionson 31 other servers

    “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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • pagestring“Which page of the site, as its path ("/about", "/contact").”
    • site_keystring“The site whose undo history to list.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • restore_versionon 6 other servers

    “Puts a site back to a version from list_versions - the undo button for AI edits.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    4 inputs, 1 required
    • pagestring“Which page of the site, as its path ("/about", "/contact").”
    • site_keystring“The site to restore.”
    • version_idintegerrequired“The version to restore, from list_versions.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • import_imageon 3 other servers

    “Copies a photo from a public URL (e.g.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    6 inputs
    • urlstring“Public http(s) URL of a JPEG, PNG, WebP, GIF or AVIF image (e.g.”
    • data_base64string“The image itself, base64-encoded (or a data:image/...;base64, URL) - for photos with no public URL, e.g.”
    • filenamestring“Optional original file name, for your own reference; the type is detected from the bytes.”
    • formatstring“Stored format.”
    • site_keystring“The site the image is for; it counts against that site owner's image allowance.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • 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.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    9 inputs
    • site_keystring“The site the record is about.”
    • business_namestring“The client business name.”
    • contact_namestring“The person to talk to at the business.”
    • contact_emailstring“Their email.”
    • contact_phonestring“Their phone.”
    • source_urlsarray“The business's own pages the site's facts came from (http/https, max 20).”
    • statusstring“Where the relationship stands.”
    • notesstring“Free-text notes (max 5000 chars).”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • 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.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    2 inputs, 1 required
    • site_keystringrequired“The managed site to hand over to a departing client.”
    • include_domainboolean“Move the site's connected domain with it (default true).”
  • publish_staged

    “Makes a site's staged changes (edit_section/set_theme with stage: true) live.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    2 inputs
    • site_keystring“The site whose staged changes should go live.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • discard_staged

    “Drops a site's staged changes without touching the live site.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    2 inputs
    • site_keystring“The site whose staged changes should be dropped.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • “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.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    8 inputs
    • site_keystring“The site to theme.”
    • palette_primarystring“New primary brand colour as a #rrggbb hex string.”
    • palette_neutralstring“New neutral text/background colour as a #rrggbb hex string.”
    • font_headingstring“New heading font family name.”
    • font_bodystring“New body font family name.”
    • favicon_urlstring“The browser-tab icon for the site: an https:// image URL (or a /path on the site), max 500 characters.”
    • stageboolean“true = work on a staged copy instead of the live site: preview it at staged_preview_url, then publish_staged or discard_staged.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • get_preview_urlon 4 other servers

    “Returns the shareable preview URL for a site, plus its expiry.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • site_keystring“The site to preview.”
    • share_idstring“Alternative lookup by share id, honoured only when it belongs to the caller.”
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”
  • draft_create

    “Mints an anonymous draft identity (a draft token) with no account and no sign-in.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    1 input
    • namestring“Optional display name for the draft site.”
  • export_site_html

    “Renders a site to a single self-contained HTML file.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • site_keystringrequired“The site to export.”
  • draft_claim

    “Moves an anonymous draft onto the account of the signed-in user after they have authorized.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input
    • draft_tokenstring“The draft token to claim.”
  • domain_searchon 1 other server

    “Checks availability and price for a domain, or for a bare name across a set of TLDs.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    3 inputs, 1 required
    • querystringrequired“A full domain (name.tld) or a bare name to check across TLDs.”
    • tldsstring“Comma-separated TLDs to check a bare name against, e.g.”
    • limitinteger“Max number of results to return (default: all, max 25).”
  • purchase_linkon 1 other server

    “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.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    1 input, 1 required
    • domainstringrequired“The full domain to buy, e.g.”
  • purchase_execute

    “Charges the saved card of the customer immediately for a purchase they have explicitly agreed to in this conversation.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    6 inputs, 6 required
    • kindstringrequired“What is being bought.”
    • itemstringrequired“The exact thing being bought; for kind='domain', the full domain name.”
    • consent_confirmedstringrequired“Pass 'user_confirmed' ONLY after the customer has explicitly agreed to this exact purchase and amount in the conversation.”
    • consent_itemstringrequired“The item the customer agreed to buy, as they understood it.”
    • consent_amount_centsintegerrequired“The exact amount in cents the customer agreed to pay.”
    • consent_statementstringrequired“The customer's own words agreeing to this purchase, relayed verbatim.”
  • domain_registeron 1 other server

    “Completes registration for a domain the customer has ALREADY paid for.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    1 input, 1 required
    • domainstringrequired“The full domain to register, e.g.”
  • 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, keep…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    7 inputs, 2 required
    • site_keystringrequired“The site the business is paying for (must be yours, and not yet live on a domain).”
    • domainstringrequired“The domain to register for them, bare, e.g.”
    • price_centsinteger“Custom price in cents per interval.”
    • intervalstring“Billing interval.”
    • business_namestring“The business name shown on the pay page.”
    • contact_emailstring“The business owner's email, for your records (Stripe also collects it at payment).”
    • dry_runboolean“true = quote only: runs every check and returns price, setup fee and registrar, but creates NO pay link.”
  • 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.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs
    • codestring“The link code: the pcl_… part at the end of pay_url.”
    • site_keystring“Or the site whose open pay link to cancel.”
  • “Changes a site's display name (shown in list_sites and the dashboard).”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    6 inputs
    • site_keystring“The site to rename.”
    • namestring“The new display name, plain text, e.g.”
    • page_titlestring“Optional browser-tab / search title for the home page (max 70 characters).”
    • page_descriptionstring“Optional search-snippet and link-preview description for the home page, 1-300 characters.”
    • og_image_urlstring“Optional link-preview (share card) image for the home page: an https:// image URL, max 500 characters.”
    • stageboolean“true = put the home page title change on the staged copy (publish_staged makes it live).”
  • 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 t…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    9 inputs, 4 required
    • site_keystringrequired“The site the form belongs to.”
    • stageboolean“true = stage this form change with the page: visitors keep the live form until publish_staged (discard_staged drops it); preview at staged_preview_url.”
    • form_keystring“Omit to create a new form; pass an existing form_key (from a previous call) to update that form.”
    • namestringrequired“The form's name, used in the notification subject "<Site name>: new <name>", e.g.”
    • recipient_emailstringrequired“Where entries are emailed.”
    • fieldsarrayrequired“1-20 fields, in display order.”
    • submit_labelstring“Button text.”
    • success_messagestring“Shown after a successful entry.”
    • classesobject“Optional Tailwind/CSS class strings to style the form to match the page.”
  • list_form_submissionson 4 other servers

    “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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    4 inputs, 1 required
    • site_keystringrequired“The site whose form entries to list.”
    • form_keystring“Optional: only entries from this form.”
    • limitinteger“How many entries, newest first.”
    • include_previewboolean“Also list test entries sent from a staged preview (they are marked as preview entries).”
  • “Page views and unique visitors per day for a published site, plus its top pages and the websites that sent visitors.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • site_keystring“The site whose visits to read.”
    • daysinteger“How many days back, including today (UTC).”
  • “Puts a finished site live on the domain the user has connected.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    2 inputs, 2 required
    • site_keystringrequired“The site to publish.”
    • domainstringrequired“The domain to publish to, e.g.”
  • payment_statuson 13 other servers

    “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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input
    • domainstring“Optionally narrow to a single domain, e.g.”
  • “Reports who the caller currently is: an authenticated account, an anonymous draft holder, or nobody.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • draft_tokenstring“The draft token returned by draft_create, if you are working on an anonymous draft.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-18.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
100% of 169
Tools with a description
100% of 41
Typical description length
351 characters

The tool set

Counted from the listing

Tools
41
Size of the list
about 16,247 tokens for an agent to load (characters ÷ 4)
Naming
40 of 41 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 41 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-18 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://pagetool.io/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "pagetool": {
      "url": "https://pagetool.io/api/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "pagetool": {
      "type": "http",
      "url": "https://pagetool.io/api/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"pagetool","type":"http","url":"https://pagetool.io/api/mcp"}'
Claude Code
claude mcp add --transport http pagetool https://pagetool.io/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "pagetool": {
      "type": "streamableHttp",
      "url": "https://pagetool.io/api/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "pagetool": {
      "httpUrl": "https://pagetool.io/api/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.pagetool]
url = "https://pagetool.io/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "pagetool": {
      "url": "https://pagetool.io/api/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://pagetool.io/api/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

  • MCP SDK in the package files. Not read yet: added with the next daily run.
  • Build workflow. Not read yet: added with the next daily run.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-18. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-18. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-18. Source: read 2026-11-18.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-18. Source: read 2026-11-18.

Own host

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint pagetool.io/api/mcpSession openedmatchesour test · 2026-11-18
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-18

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-18. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about io.pagetool/pagetool

Answered from the data above

Who publishes io.pagetool/pagetool?

The registry ties the namespace io.pagetool to the domain pagetool.io; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Does io.pagetool/pagetool need an API key or sign-in?

It opened a session without any credential on 2026-11-18. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.pagetool/pagetool been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-18
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 3
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-11-18, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,254 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 41 tools, 0 resources, 0 prompts.
  4. 4,443 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-18; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-11-18
MCP capability
tools
our test · 2026-11-18
Transport
streamable HTTP
registry · 2026-11-18
Required credentials
none declared
registry · 2026-11-18 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-18
Lifecycle status
registry · 2026-11-18
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-18

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.pagetool/pagetool: MCP server record.” Data checked 2026-11-18. https://protocolprobe.com/mcp/servers/io.pagetool/pagetool

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.pagetool/pagetool)](https://protocolprobe.com/mcp/servers/io.pagetool/pagetool)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology