
Pagefully MCP server
Which MCP servers are Pagefully's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namecom.pagefully/mcpverified in the MCP registry
The registry name sits under pagefully.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools15
- Server calls itselfpagefully
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 1240 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- update_plan, add_screens, edit_page, publish_pages, confirm_publish change data without a sign-in: anyone with the address can call them.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer1371 ms
- Space in an agent's context≈ 8,076 tokensthe definitions of all its tools (15), which an agent carries on every turn
- Tool definitionsA · 98 of 100
- Typed results0 of 15 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 15
Worth a look
- Tools that change data, on a server that answers without a sign-in: update_plan, add_screens, edit_page, publish_pages, confirm_publish
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
analyze_appReads an iOS app from its App Store link or id and says what Pagefully understood of it. Call this first. Signed in (OAuth or a Pagefully token): adds the app to the workspace (no App Store Connect key is needed to plan and make pages)…
propose_planReturns the app's plan: one custom product page for each search intent. Each intent has a kind (problem, feature or competitor), what its page says, and the keywords from the app's keyword field that the page claims. A keyword belongs to…
update_planChanges the plan in one call, as the person asked: add an intent, update one (its name, what its page says, or on and off), approve (switch on) a list, remove a list, or reorder (the order is build priority). Changes apply in that order…
add_screensAdds screens of the app for pages to be drawn from: captures of the running app, beside the screenshots its App Store listing already has. Use it when the listing's screenshots are stale, when a page needs a screen the listing does not…
generate_pagesMakes a page for every intent that is switched on and has none: the words are written, drawn onto the app's own screenshots, and checked against App Review's rules (pre-flight). Each page is its own job. Returns the jobs with their page…
get_jobThe state of a long job: queued, running, done or failed, with its steps as progress, counts of what it did, and the code and message of what went wrong. Call it after any tool returned a job_id, every few seconds, until the state is done…
edit_pageChanges one screenshot on a page, or several in one call, makes one again, or approves the page. Say which screenshot by position (1 is the first) or slot_id. By hand: its headline, its subline, the screen it shows ("screen", a position…
preview_pageOne page, whole: each screenshot with its headline, subline and picture, the promotional text, the keywords it is for, what pre-flight found, whether it is approved, and its preview_url on pagefully.com. The screenshots also come back as…
publish_pagesStep one of two. Sends nothing. Returns exactly what would be made in App Store Connect for the pages asked for (each page's name, headlines, promotional text, keywords, devices, whether it is a revision, and its preview_url), which pages…
confirm_publishStep two of two. Spends the confirmation_token from publish_pages and makes each page in the summary in App Store Connect, one job for each page. Returns the jobs: call get_job for each. Call it only after the person has seen the summary…
get_resultsHow each page is doing on the App Store against the app's default page over the last seven days Apple has reported: views, downloads and conversion rate for each page and for the default page, and by source. The numbers are Apple's, and…
suggest_refreshThe pages Pagefully suggests the app should have and does not: each with a name, a kind, what the page would say, the searches it is for and the reason. These are the suggestions the product already holds (such as a use the app's…
get_usageFor each app on the workspace: its plan (Free, the Pack or Pro, which belong to an app), pages made and allowed, what is left, revisions used for each page, and the address of its plan screen. Also what each plan allows and costs, the…
search_screenshotsSearches the App Screenshot Index: every screenshot of the top 100 free apps in each App Store category (United States), read and tagged by what it does. Needs no account. Use it to see how the leading apps in a category design their…
score_screenshotsReads a set of screenshots with the App Screenshot Index's own reader and holds it against a category: each screenshot comes back with the same tactic keys search_screenshots uses (with label and group), its words and its colour, and each…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"pagefully": {
"type": "http",
"url": "https://pagefully.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http pagefully https://pagefully.com/api/mcpclaude.ai, ChatGPT and other clients: add https://pagefully.com/api/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.