Skip to content
Agents tracked: 502 Releases (7d): 762 Agent status: no reported issuesSince last limit reset: Claude 11d · Codex 9d For AI agents: Markdown Updated Nov 22, 2026

Appllama

by Appllama

study top-earning iPhone app screens before building.

OtherOfficialRemote

GitHubWebsite

1. Made by

“"homepage": "https://appllama.io/mcp", "repository": "https://github.com/Appllama/appllama-skills"”

The repository belongs to the Appllama organization, its plugin files name Appllama (appllama.io) as author, and the server wraps Appllama's own library at mcp.appllama.io. The server's code itself is not public.

github.com/Appllama/appllama-skills/blob/dd5caaec3d5d50ad7fc0324da238119c6b7c3707/.claude-plugin/plugin.json

Checked against its repository at one commit, on Nov 10, 2026. Tap a verdict to see its source.How we checkedReport an error

What Appllama does

Appllama is a paid library of real screens from top-earning iPhone apps, with their revenue and download numbers. Its connector lets your AI assistant search those apps, walk through their screens and study onboarding and paywalls, then build your app from what it found. It needs an Appllama Pro plan.

What people use it for

Study the leaders before building

Before your assistant builds a habit tracker, it looks up the top-earning habit apps and walks their screens one by one.

Plan onboarding and the paywall

See how many steps winning apps put in onboarding, what each step asks and where the paywall appears.

Improve one screen you already have

Paste a screen id copied on appllama.io or a screenshot, and the assistant pulls similar screens from strong apps to compare.

Learn how leaders build one element

Look at how top apps draw a tab bar, a progress bar or an empty state before your assistant builds its own.

Start from your saved boards

If you already saved screens on appllama.io, the assistant opens that board first instead of searching again.

Appllama popularity

5,227
GitHub stars, Appllama/appllama-skills
0
public agent projects connect it
Appllama: GitHub starsAppllama/appllama-skills 5,227

Tools it gives your agent (12)

What it sends and its license

Sends

your searches and screen requests, tied to your account

To Appllama (mcp.appllama.io); on every tool call; usage is checked and watched for bulk retrieval. Opt out: none while connected; disconnect or ask Appllama to revoke the connection.

The connector is paid (Pro) and licensed to one person for research, reference and design inspiration. The screens belong to the apps' owners, so do not copy them, republish them or train models on them.

In a paid app
With conditions

You may study the library and build your own paid app from what you learn, but not copy or republish its screens.

“Through it, an agent working on the member's behalf may search apps, walk their screens, and study flows and UI elements, and may build from what it finds.” source

Pass on its files
No

Republishing, reselling or redistributing library content is not allowed.

“republish, resell, syndicate or otherwise redistribute content from the library” source

ai-training
No

Training, fine-tuning, evaluating or indexing a model with the library is not allowed.

“use it to train, fine-tune, evaluate, benchmark or index a machine learning model” source

client-work
With conditions

Study for a client is research use, but the plan is for one named person and the login may not be shared.

“Sharing account credentials, or allowing another person to use your account, is not permitted.” source

Is it alive

Latest version

1.0.1 in the registry, updated Aug 27, 2026

Last release

registry version 1.0.1 (2026-08-27); repository last changed 2026-09-06

Remote endpoint
yes: one unauthenticated GET to https://mcp.appllama.io/mcp answered 401 (sign-in required) on 2026-11-10

Alternatives

Appllama This page

5,227 starsRemote

mobbin

Pick it if you also need web app screens, not only mobile

Local

screensdesign

Pick it if you want another library of top-grossing iOS onboarding flows and paywalls

Local

All other servers

Get started

Tell your AI assistant

“Connect the Appllama MCP at https://mcp.appllama.io/mcp, call get_credits, then study the top three apps in my category screen by screen and write notes with screen ids only; do not download or keep the images.”

Connect it

{
  "mcpServers": {
    "Appllama": {
      "type": "http",
      "url": "https://mcp.appllama.io/mcp"
    }
  }
}

The claude_code entry is the repository's .mcp.json and the cursor entry its mcp.json for the Cursor plugin. For Codex and other clients the README only says to add the address as a custom connector. Sign-in is OAuth with your Appllama account.

Mistakes to avoid

Downloading every studied screen into a local research/img folder, as the vendor's own usage skill suggests
Keep notes and screen ids; fetch a fresh link from the id when you need to look again

The terms say media links are for immediate study, not storage, and forbid caching or archiving the library.

Looping over every page of search results to collect the whole catalog
Study the few apps that matter for the task

Bulk retrieval is detected and gets the account restricted, and every call spends a credit.

Jumping to page 3 of a list or reusing a cursor with a new query
Page through in order, passing next_cursor back with the same query; restart from page one if a cursor errors

Pagination only goes forward, one page at a time.

Rebuilding a screen with the Appllama watermark or another app's logo in it
Rebuild the pattern in your own design

The watermark is provenance and the logos belong to the apps' owners.

Questions

Is it free?

No. The connector is part of the paid Pro plan, with 1,500 credits a month; browsing the site has a free part.

Can I copy the screens into my app?

No. You may study them for research and inspiration and build your own; the screens and logos stay with the apps' owners.

Can I use the screens to train an AI model?

No. The terms forbid training, fine-tuning, evaluating or indexing a model with the library.

Do I have to install the skills?

No. The connector works on its own; the free skills only teach an assistant how to research with it and how to build native screens.