Capacitor Mcp logo

Capacitor Mcp

Organization
Cap-go
capacitor-mcp

Model Context Protocol (MCP) tools for Capacitor mobile development. Covers Ionic/Capacitor component APIs, plugin documentation, CLI commands, and AI-assisted development via MCP. Use this skill when users want to integrate AI agents with Ionic/Capacitor tooling.

Overview

PublisherCap-go
Repositorycapgo-skills
Skill namecapacitor-mcp
Stars
71
Forks
4
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Cap-go on GitHub. Read the source before you install it.

Installation

Install the Capacitor Mcp AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Cap-go/capgo-skills.git /tmp/capgo-skills
mkdir -p .claude/skills
cp -r /tmp/capgo-skills/plugins/capacitor-core/skills/capacitor-mcp .claude/skills/capacitor-mcp
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Capacitor Mcp in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Capacitor Mcp on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Capacitor Mcp is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Capacitor MCP Tools

Guide to using Model Context Protocol (MCP) for Ionic and Capacitor mobile development automation.

When to Use This Skill

  • User wants to automate Ionic/Capacitor development
  • User asks about MCP integration
  • User wants AI-assisted component/plugin discovery
  • User needs programmatic CLI command execution
  • User wants access to Ionic components and Capacitor plugins within AI chat

What is MCP?

MCP (Model Context Protocol) is an open standard for connecting AI models to external tools and data sources. For Capacitor development, MCP enables:

  • Access to Ionic component definitions and APIs
  • Capacitor plugin documentation lookup
  • Automated CLI command execution (build, sync, run, etc.)
  • Project configuration management
  • Real-time component demos and examples

Setting Up MCP for Capacitor

1. Install Awesome Ionic MCP Server

The awesome-ionic-mcp server is a comprehensive tool that provides access to:

  • Ionic Framework component APIs
  • Official Capacitor plugins
  • third-party plugin catalogs
  • Capacitor Community plugins
  • CapGo plugins
  • 28 Ionic/Capacitor CLI commands
Claude Desktop

Add to claude_desktop_config.json (accessible via Claude > Settings > Developer):

json
{
  "mcpServers": {
    "awesome-ionic-mcp": {
      "command": "npx",
      "args": ["-y", "awesome-ionic-mcp@latest"]
    }
  }
}
Cline

Add to cline_mcp_settings.json:

json
{
  "mcpServers": {
    "awesome-ionic-mcp": {
      "command": "npx",
      "args": ["-y", "awesome-ionic-mcp@latest"],
      "disabled": false
    }
  }
}
Cursor

Add to .cursor/mcp.json (project-specific) or ~/.cursor/mcp.json (global):

json
{
  "mcpServers": {
    "awesome-ionic-mcp": {
      "command": "npx",
      "args": ["-y", "awesome-ionic-mcp@latest"]
    }
  }
}

2. Optional: GitHub Token for Rate Limiting

The server makes ~160+ GitHub API calls during initialization to fetch plugin data. Without authentication, GitHub limits you to 60 requests/hour. With a token, this increases to 5,000 requests/hour.

Add GITHUB_TOKEN to your MCP configuration:

json
{
  "mcpServers": {
    "awesome-ionic-mcp": {
      "command": "npx",
      "args": ["-y", "awesome-ionic-mcp@latest"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

Get a token from GitHub Settings → Developer settings → Personal access tokens. No special permissions needed for public repos.

Available MCP Tools

Ionic Component Tools

typescript
// Get Ionic component definition
get_ionic_component_definition({ tag: "ion-button" })
// Returns TypeScript definition from @ionic/core

// List all Ionic components
get_all_ionic_components()
// Returns: ["ion-button", "ion-card", "ion-input", ...]

// Get component API documentation
get_component_api({ tag: "ion-button" })
// Returns API docs from ionicframework.com

// Get component demo code
get_component_demo({ tag: "ion-modal" })
// Returns demo code from docs-demo.ionic.io

Capacitor Plugin Tools

typescript
// Get official Capacitor plugin API
get_official_plugin_api({ plugin: "Camera" })
// Returns documentation from capacitorjs.com

// List all official plugins
get_all_official_plugins()
// Returns: ["Camera", "Filesystem", "Geolocation", ...]

// Search all available Capacitor plugins
get_all_capacitor_plugins()
// Returns superlist from all plugin publishers

// Get third-party plugin documentation
get_plugin_api({ plugin: "capacitor-firebase" })

// List third-party plugins
get_all_free_plugins() // Free plugins
get_all_insider_plugins() // Insider/paid plugins

// Get CapGo plugin documentation
get_capgo_plugin_api({ plugin: "native-biometric" })
get_all_capgo_plugins()

// Get Capacitor Community plugin docs
get_capacitor_community_plugin_api({ plugin: "http" })
get_all_capacitor_community_plugins()

Ionic CLI Commands

All commands accept a project_directory parameter (defaults to current directory).

Project Information
typescript
// Get comprehensive project info
ionic_info({ format: "json" })

// Get configuration value
ionic_config_get({ key: "name" })

// Set configuration value
ionic_config_set({ key: "name", value: "MyApp" })

// Unset configuration value
ionic_config_unset({ key: "telemetry" })
Project Setup
typescript
// Create new Ionic project
ionic_start({
  name: "MyApp",
  template: "tabs", // blank, list, sidemenu, tabs
  type: "react", // angular, react, vue
  capacitor: true
})

// List available templates
ionic_start_list()

// Initialize existing project
ionic_init({ name: "MyApp", type: "react" })

// Repair project dependencies
ionic_repair()
Build & Serve
typescript
// Build web assets
ionic_build({
  project_directory: "./my-app",
  prod: true,
  engine: "browser" // or "cordova"
})

// Start development server (manual launch recommended)
// Note: Server runs in foreground, manual launch preferred
ionic_serve({
  project_directory: "./my-app",
  port: 8100,
  lab: false
})
Code Generation
typescript
// Generate page
ionic_generate({
  type: "page",
  name: "home",
  project_directory: "./my-app"
})

// Generate component
ionic_generate({
  type: "component",
  name: "user-card"
})

// Generate service
ionic_generate({
  type: "service",
  name: "auth"
})

// Other types: directive, guard, pipe, class, interface, module
Integrations
typescript
// List available integrations
integrations_list()

// Enable integration (e.g., Capacitor)
integrations_enable({ integration: "capacitor" })

// Disable integration
integrations_disable({ integration: "cordova" })

Capacitor CLI Commands

Project Management
typescript
// Check Capacitor setup
capacitor_doctor({ platform: "ios" })

// List installed plugins
capacitor_list_plugins()

// Initialize Capacitor
capacitor_init({
  name: "MyApp",
  id: "com.example.app",
  web_dir: "dist"
})

// Add platform
capacitor_add({ platform: "ios" })
capacitor_add({ platform: "android" })

// Migrate to latest version
capacitor_migrate()
Build & Sync
typescript
// Sync web assets and dependencies
capacitor_sync({ platform: "ios" })

// Copy web assets only
capacitor_copy({ platform: "android" })

// Update native dependencies
capacitor_update({ platform: "ios" })

// Build native release
capacitor_build({
  platform: "ios",
  scheme: "App",
  configuration: "Release"
})
Run & Deploy
typescript
// Run on device/emulator
capacitor_run({
  platform: "ios",
  target: "iPhone 15 Pro"
})

// Open native IDE
capacitor_open({ platform: "ios" }) // Opens Xcode
capacitor_open({ platform: "android" }) // Opens Android Studio

Common Workflows

Create New Project

typescript
// 1. Create Ionic project
ionic_start({
  name: "MyApp",
  template: "tabs",
  type: "react",
  capacitor: true
})

// 2. Add iOS platform
capacitor_add({
  project_directory: "./MyApp",
  platform: "ios"
})

// 3. Build and sync
ionic_build({
  project_directory: "./MyApp",
  prod: true
})
capacitor_sync({
  project_directory: "./MyApp",
  platform: "ios"
})

Check Project Health

typescript
// Get system info
ionic_info({ format: "json" })

// Check Capacitor setup
capacitor_doctor({ platform: "ios" })

// List installed plugins
capacitor_list_plugins()

Generate Code

typescript
// Generate page with routing
ionic_generate({ type: "page", name: "profile" })

// Generate reusable component
ionic_generate({ type: "component", name: "user-avatar" })

// Generate service
ionic_generate({ type: "service", name: "data" })

AI-Assisted Development Benefits

With awesome-ionic-mcp, AI assistants can:

  1. Discover Components: Ask "What Ionic components can I use for forms?" and get accurate API docs
  2. Find Plugins: Ask "Is there a Capacitor plugin for biometric authentication?" and get relevant results
  3. Execute Commands: Request "Build the iOS app" and the CLI command runs automatically
  4. Generate Code: Get component examples with proper TypeScript definitions
  5. Troubleshoot: Look up plugin APIs and configuration without leaving the chat

Example Queries

With the MCP server installed, you can ask your AI assistant:

  • "Show me the API for ion-modal component"
  • "List all available Capacitor Camera plugin methods"
  • "Generate a new page called settings"
  • "What third-party plugins are available for Firebase?"
  • "Build my app for iOS"
  • "Sync my Capacitor project"
  • "What are all the free CapGo plugins?"

Technical Details

Data Sources

The awesome-ionic-mcp server aggregates data from:

  • @ionic/core package (TypeScript definitions)
  • ionicframework.com (component API docs)
  • docs-demo.ionic.io (component demos)
  • capacitorjs.com (official plugins)
  • third-party plugin catalogs
  • capacitor-community (community plugins)
  • capgo.app (CapGo plugins)

Requirements

  • Node.js (for npx command)
  • Optional: GitHub token for avoiding API rate limits
  • Ionic/Capacitor project (for CLI commands)

Browser Automation

The server uses Puppeteer to fetch some documentation. You may see a browser window spawn and close during initialization - this is normal.

Resources

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Capacitor Mcp AI skill do?

Model Context Protocol (MCP) tools for Capacitor mobile development. Covers Ionic/Capacitor component APIs, plugin documentation, CLI commands, and AI-assisted development via MCP. Use this skill when users want to integrate AI agents with Ionic/Capacitor tooling.

Why use Capacitor Mcp on TypingMind?

Because you install it once and use it with any model. Capacitor Mcp is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Capacitor Mcp in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Cap-go/capgo-skills/tree/main/plugins/capacitor-core/skills/capacitor-mcp. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Capacitor Mcp?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Capacitor Mcp?

As many as you like. As long as a model supports skills, you can use Capacitor Mcp with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Capacitor Mcp AI skill free?

It is published on GitHub by Cap-go. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇