edit_page
shallowcom.pagefully/mcp · Verify this server
Changes 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 from preview_page's screens or add_screens), its style, or its design. The screenshot is drawn again and checked again, and returns with the page. To change several screenshots of one page, send "changes": a list with one item for each screenshot (its position or slot_id, and what to change), in place of the single form. They are made in order, each screenshot once. Set "return" to "changed" to get back only the screenshots that changed and not the whole page, which is much shorter. A hand change is never counted against a plan, in a list or alone. Not every screenshot can take every change, and the answer says which did. Each slot in preview_page has "design" and "own_words". design "ours": the app's screen in Pagefully's own design, where a headline, a subline and a style all apply. design "theirs": the developer's own designed screenshot with only its words changed, where a style has nothing to change. own_words true: new words could not be set on that design, so the picture is exactly as the developer made it and a headline cannot be put on it. design "kept": a poster with no headline of its own, left whole. "changes" in the answer lists, for each screenshot, what was changed and what was not, with the reason and what to do. When nothing in the call could be applied the answer is an error (code words_kept, kept_whole or style_not_ours) and the page is as it was: tell the person the reason as it is. The way to put new words or a style on such a screenshot is "design": "ours", which draws its screen in Pagefully's own design on every page of the app that shows that screen, so send it only when the person asks for it; or put another screen on it with "screen". Set regenerate to have Pagefully make it again: "headline" writes new words for that screenshot, "background" gives it the next style, "screen" puts the next unused screen on it, and "page" writes and draws the whole page again as a job (call get_job, then preview_page). Each regenerate counts against the month's rewrites for the plan: when they are used the answer is upgrade_required, which you repeat as it is. Changing words by hand is not counted. Regenerate only when the person asks for a fresh attempt. Any edit withdraws the page's approval, so what is approved is always what was last seen. Set approve to true only after the person has looked at the page's preview_url and said yes to it: approval is their explicit click, not yours. A page cannot be approved while its pre-flight has a failure. If the answer has code own_words, some screenshots still show the developer's own words: ask the person, and send own_words true only if they say to approve it as it is. Never write another app's name, a ranking, an award or a price into a headline: pre-flight fails it. Adding or removing a screenshot, the promotional text and the keywords are changed on the page's preview_url in the web app.
1 trials · measured 1 day ago
edit_page scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against com.pagefully/mcp, measured 20 Oct 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- gated
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-10-20 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/a6b4587f-d322-4572-9c78-30f0432bcc4a)