search_screenshots
shallowcom.pagefully/mcp · Verify this server
Searches 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 screenshots before you plan, write or review a page, and to hold a page against what its category does. Four ways to call it. (1) With nothing: the catalogue, every category and every tactic with its key, what it means and how common it is. Tactics are grouped: meaning (what the words lead with: a problem, an outcome, a feature, who it is for, trust), words (headline length, where the words sit), layout (how the phone is drawn), look (colour, light or dark, a person in the picture) and proof (a rating, an award, a number of users, a press name, a quoted review). There are also tactics of a whole set (set_...): one template throughout, proof on the first screenshot, and so on. (2) With a category alone: every tactic used in that category, with the top ten apps beside the rest, and the keys nobody in it uses. (3) With app: one app's whole set in order, what each screenshot leads with, and what the set does as a whole (whether one colour holds, whether the first screenshot is laid out differently, how many carry a headline). This is how to study a set's story. (4) With any filter: the screenshots that match. Filters: query (words the screenshot says, or an app's name), tactics (a screenshot must carry all of them), any_tactics (it must carry at least one), category, colour, top_ten_only, and screenshot_position (1 for first screenshots only: the first one does a different job from the rest). A result has the words on the screenshot, every tactic it carries, its set's tactics, its colour, the app and its chart position, the picture's address and its page on the Index. When tactics are given the answer says how common each is, and seen_with names what else the matching screenshots share more often than screenshots in general. Set detail to "compact" to read many at once: tactic keys with no labels, no count by category, up to 80 screenshots in a call. Set with_images to look at the first 8 pictures yourself, small. What the numbers mean: they describe what the leading apps do. They do not show that a tactic causes installs or rank, so say "most top Finance apps do this", never "this will raise your rank". Another app's words and name are for understanding a category. Never copy them into a page, and never name another app in copy.
1 trials · measured today
search_screenshots 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/328873f9-2707-4cb7-8da0-6e3e8030898f)