Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Model Context Protocol (MCP) Server: io.appllama/appllama
This MCP server is associated with “appllama,” described as a builder that “study screens, flows and paywalls from top-earning iOS apps” to help create agent skills for building mobile apps. Its focus area includes mobile app development, mobile design, and model-context-protocol, with supporting topics for Claude and coding tools.
🛠️ Key Features
Builds “agent skills” for mobile app development
Studies mobile screens, user flows, and paywalls from top-grossing iOS apps
Mentions a “simulator-verified bar” for completed skills
Includes “mcp” and “model-context-protocol” as topics
🚀 Use Cases
Developing mobile-design and mobile-UI capabilities for AI agents
Building and improving agent workflows for iOS app screens and flows
Applying learned patterns to skills related to paywalled experiences
⚡ Developer Benefits
Reusable “agent skills” aimed at building mobile apps
Grounded in examples from top-earning iOS applications
Topics indicate compatibility with agent tooling ecosystems (e.g., Claude, Cursor)
⚠️ Limitations
Source data does not provide a tool list or detailed MCP endpoints (only topics and a partial README excerpt).
Appllama is the design library of top-grossing mobile
apps — their real screens, flows, and UI patterns, with revenue and download
context. These skills turn that library into an agent's working method:
study every screen of the apps that already win, extract the category's
design language, then build screens that hold up next to them.
The research engine: how to use the Appllama MCP like a design director — the full tool map, and the playbooks for building an app from scratch, improving an existing screen, and flow & element research.
The build bar: native-feeling Expo / React Native screens — Apple HIG fidelity, semantic colors, native controls, anti-slop discipline, navigation that behaves (push vs replace, sheets and overlays, the one-way doors where back must not exist), a strict motion bar (should it animate at all, springs that carry the finger's velocity, nothing on the JS thread), generated image assets, and a full-motion simulator loop (whole flows recorded and scrubbed frame by frame, not screenshots).
They are designed as a pair: usage decides what to study, design
decides how to build, and both insist the loop only ends in a simulator
with a screen you can't fault.
Install
One command, from your project root — works with Claude Code, Cursor,
Codex, and 70+ other agents:
bash
npx skills@latest add appllama/appllama-skills
Variations:
bash
# install for specific agents, no prompts
npx skills@latest add appllama/appllama-skills -a claude-code -a cursor -y
# install user-wide instead of per-project
npx skills@latest add appllama/appllama-skills -g
Only want the app design skill?
appllama-app-design-skill stands on its own — the native-quality build
bar, anti-slop discipline, and the full-motion simulator loop work with or
without the Appllama MCP connected:
(The same --skill flag installs only appllama-usage if you want just the
research engine.)
Manual install
Skills are plain directories — copy them into your agent's skills folder
(.claude/skills/ per project, ~/.claude/skills/ user-wide, or your
harness's equivalent):
appllama-usage runs on the Appllama MCP; appllama-app-design-skill is
sharper with it connected. The endpoint:
code
https://mcp.appllama.io/mcp
Add it as a custom connector in Claude, Cursor, Codex, or any MCP client
and approve the connection with your Appllama account. MCP access is part
of Pro; credits reset in full on the 1st of
each month. Every call spends one credit — get_credits is always free.
Try it
With the MCP connected and the skills installed, ask your agent:
Build me a habit tracker. Study the top-grossing habit apps first and
don't stop until every screen survives the simulator comparison.
Make this screen better. (paste a screenshot, code, or a "Copy Screen
ID" ref from appllama.io)
How do the best fitness apps structure onboarding — how long, what does
each step earn, and where does the paywall sit?
Wire up the checkout flow. Decide which screens push, which present as
sheets, and make sure nobody can go back into the paywall after paying.
Review the animations in this app — what should be deleted, what's on the
wrong thread, what's missing velocity — and give me the plan.
License
MIT. The Appllama name, llama, and logo are trademarks of
Antmind Ventures Private Limited — the license does not grant rights to
use them.
