PluginBench
MCP Server
Active
MIT

Appllama MCP Server

io.appllama/appllama

Study top-grossing iOS apps and build native-quality screens with AI agents.

What is the Appllama MCP server?

Appllama is an MCP server that connects AI agents to a design library of top-grossing mobile apps, enabling them to research real screens, flows, and UI patterns, then build native-feeling Expo/React Native apps verified in a simulator. It provides two complementary skills: appllama-usage for design research and appllama-app-design-skill for high-fidelity native builds with anti-slop discipline.

Appllama gives AI agents access to screens, flows, and design patterns from top-earning iOS apps, plus tools to build native-quality mobile apps that hold up against them. Use it to research category design languages, improve existing screens, understand paywall and onboarding flows, and generate simulator-verified React Native code with proper animations, semantic colors, and Apple HIG compliance.

How to install Appllama

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
~/.cursor/mcp.json
{
  "mcpServers": {
    "appllama": {
      "url": "https://mcp.appllama.io/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • appllama-usage — Research engine for studying top-grossing apps—full tool map, playbooks for building from scratch, improving screens, and researching flows and UI elements.
  • appllama-app-design-skill — Build bar for native-feeling Expo/React Native screens with Apple HIG fidelity, semantic colors, native controls, motion discipline, and full-motion simulator verification.
  • get_credits — Check remaining Appllama MCP credits (always free).

Use cases

  • Build a new mobile app by first studying top-grossing competitors in the category, then generating simulator-verified screens.
  • Improve an existing screen by comparing it against high-performing apps and applying their design patterns.
  • Research onboarding and paywall flows to understand how top apps structure user acquisition and monetization.
  • Generate production-ready React Native code with proper navigation (push vs replace, sheets, overlays) and motion that respects performance.
  • Review and fix animations in existing apps—identify what should be deleted, what's on the wrong thread, and what's missing velocity.

Appllama MCP server FAQ

What is Appllama?

Appllama is a design library of top-grossing iOS apps paired with MCP skills that let AI agents research real screens and flows, then build native-quality mobile apps verified in a simulator.

Is Appllama free?

The skills are free to install (MIT license). MCP access requires an Appllama Pro account; credits reset monthly and each API call costs one credit (get_credits is always free).

How do I install Appllama in Claude or Cursor?

Run `npx skills@latest add appllama/appllama-skills` from your project root. Then add the MCP endpoint `https://mcp.appllama.io/mcp` as a custom connector in your agent and approve with your Appllama account.

Do I need the MCP connected to use the design skill?

No—appllama-app-design-skill works standalone for building native React Native screens. The MCP connection enhances both skills by providing access to the top-grossing app library.

What does the design skill produce?

Native-feeling Expo/React Native screens with Apple HIG compliance, semantic colors, proper navigation patterns, motion discipline, and generated image assets—all verified in a full-motion simulator loop.

Can I use just the research skill without building?

Yes—install only appllama-usage with `npx skills@latest add appllama/appllama-skills --skill appllama-usage` to study app flows and design patterns without the build tools.

README (reference)

Source of truth, from the repository.

<p align="center"> <a href="https://appllama.io"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://public.appllama.io/appllama-logo-dark.png"> <img src="https://public.appllama.io/appllama-logo-light.png" alt="Appllama" width="360"> </picture> </a> </p> <h3 align="center">A builder, not just a researcher.</h3> <p align="center"> Agent skills that make AI agents genuinely good at building mobile apps —<br> studied against the top-grossing apps, finished to a simulator-verified bar. </p> <p align="center"> <a href="https://skills.sh/appllama/appllama-skills"><img src="https://skills.sh/b/appllama/appllama-skills" alt="skills.sh installs"></a> <a href="https://appllama.io"><img src="https://img.shields.io/badge/Appllama-official-1a1a1a" alt="Appllama official"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="License: MIT"></a> </p> <p align="center"> <a href="https://appllama.io">appllama.io</a> · <a href="https://appllama.io/mcp">MCP</a> · <a href="https://x.com/appllamaio">X</a> · <a href="https://www.linkedin.com/company/appllama">LinkedIn</a> · <a href="https://www.producthunt.com/products/appllama">Product Hunt</a> </p>

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 skills

SkillWhat it does
appllama-usageThe 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.
appllama-app-design-skillThe 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:

npx skills@latest add appllama/appllama-skills

Variations:

# 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:

npx skills@latest add appllama/appllama-skills --skill appllama-app-design-skill

(The same --skill flag installs only appllama-usage if you want just the research engine.)

<details> <summary>Manual install</summary>

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):

git clone https://github.com/appllama/appllama-skills
cp -r appllama-skills/skills/* ~/.claude/skills/
</details>

Connect the Appllama MCP

appllama-usage runs on the Appllama MCP; appllama-app-design-skill is sharper with it connected. The endpoint:

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.


<p align="center"> Built by <a href="https://appllama.io">Appllama</a> — the design library of top-grossing apps.<br> <a href="https://x.com/appllamaio">X</a> · <a href="https://www.linkedin.com/company/appllama">LinkedIn</a> · <a href="https://www.producthunt.com/products/appllama">Product Hunt</a> </p>

Related MCP servers

APApplyra logo

Applyra

Active

App Store Optimization data for AI agents: keyword ranks, scores, competitors, charts

0
JavaScript
MIT
View repository →
ARArcaeon logo

Arcaeon

Active

A record of what an agent did that the agent cannot quietly rewrite, and a way for anyone to check.

0
Python
MIT
View repository →

Manufacturing should-cost from CAD and drawings: cost drivers, process plan, lot sizes.

Artifact store for AI agents. Hosted OAuth at mcp.artifacta.io/mcp; local stdio via npm/PyPI.

0
TypeScript
MIT
View repository →
ASAskTheSwarm logo

Q&A network for AI agents — ask, answer, vote, earn reputation.

0
PHP
View repository →

EUR settlement + trust for AI agent commerce: budgets, KYA, merchant discovery. 22 tools.

1
Solidity
View repository →