Gluestack Mcp Tools logo

Gluestack Mcp Tools

Organization
TheBushidoCollective
gluestack-mcp-tools

Use when discovering, exploring, or retrieving gluestack-ui components via MCP tools. Provides access to component source code, variants, demos, and metadata.

Overview

PublisherTheBushidoCollective
Repositoryhan
Skill namegluestack-mcp-tools
Stars
195
Forks
20
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by TheBushidoCollective on GitHub. Read the source before you install it.

Installation

Install the Gluestack Mcp Tools 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/TheBushidoCollective/han.git /tmp/han
mkdir -p .claude/skills
cp -r /tmp/han/plugins/frameworks/gluestack/skills/gluestack-mcp-tools .claude/skills/gluestack-mcp-tools
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gluestack Mcp Tools 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 Gluestack Mcp Tools 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 Gluestack Mcp Tools 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.

gluestack-ui MCP Tools

Expert knowledge for using the gluestack-ui MCP server tools to discover, explore, and retrieve component source code and metadata.

Overview

The gluestack-ui MCP server provides direct access to the gluestack-ui component library through 6 specialized tools. Use these tools to explore available components, understand their variants, retrieve source code, and access Storybook demos.

When to Use These Tools

Use the MCP tools when you need to:

  • Discover what components are available in gluestack-ui
  • Get the actual source code for a component to copy into a project
  • Understand the variants (NativeWind, Themed, Unstyled) of a component
  • Access Storybook demos showing component usage patterns
  • Retrieve TypeScript props and dependencies for a component
  • Navigate the gluestack-ui monorepo structure

Available Tools

list_components

Lists all 70+ gluestack-ui components with their names and basic descriptions.

When to use: Start here when you need to know what components are available or find a component by name.

Example workflow:

  1. Call list_components to see all available components
  2. Identify the component that matches your needs
  3. Use get_component or get_component_metadata for details

list_component_variants

Shows the available style variants for a specific component: NativeWind, Themed, and Unstyled.

When to use: After identifying a component, use this to understand which styling approaches are supported.

Variants explained:

  • NativeWind: Tailwind CSS classes for React Native (recommended for new projects)
  • Themed: Token-based theming with design system integration
  • Unstyled: Base component with no styles (for complete customization)

get_directory_structure

Navigate the gluestack-ui monorepo to understand the package organization.

When to use: When you need to understand how gluestack-ui organizes its packages or find specific files within the repository.

get_component

Retrieves the complete source code for any gluestack-ui component.

When to use: When you need to copy component code into your project or understand the implementation details.

Example workflow:

  1. Use list_components to find the component name
  2. Use list_component_variants to choose a variant
  3. Call get_component with the component name and variant
  4. Copy the source code into your project's components/ui/ directory

get_component_demo

Accesses Storybook examples showing real-world usage patterns for components.

When to use: When you need to see how a component is used in practice, including prop combinations and composition patterns.

What you get:

  • Working code examples
  • Different prop combinations
  • Composition patterns with sub-components
  • Interactive states and variations

get_component_metadata

Retrieves TypeScript props, dependencies, and other metadata for a component.

When to use: When you need to understand the TypeScript interface, required props, or peer dependencies for a component.

Information provided:

  • TypeScript prop types and interfaces
  • Required vs optional props
  • Default values
  • Peer dependencies
  • Import statements

Common Workflows

Adding a New Component to Your Project

  1. Discover: list_components - Find the component you need
  2. Explore variants: list_component_variants - Choose NativeWind, Themed, or Unstyled
  3. Get source: get_component - Retrieve the full source code
  4. Check demos: get_component_demo - See usage examples
  5. Copy to project: Add the code to your components/ui/ directory

Understanding Component API

  1. Get metadata: get_component_metadata - See TypeScript props
  2. Check demos: get_component_demo - See prop usage in context
  3. Read source: get_component - Understand the implementation

Exploring Available Components

  1. List all: list_components - See the full component library
  2. Check structure: get_directory_structure - Understand organization
  3. Review demos: get_component_demo - See component capabilities

Best Practices

1. Start with Discovery

Always use list_components first when exploring. This gives you the canonical names to use with other tools.

# Good: Start with discovery
1. list_components -> find "Button"
2. get_component("Button", "nativewind")

# Avoid: Guessing component names
get_component("Btn") -> might not find it

2. Choose the Right Variant

  • NativeWind: Best for new projects using Tailwind CSS
  • Themed: Best when you have an existing design token system
  • Unstyled: Best when you need complete styling control

3. Check Demos Before Implementing

The Storybook demos show real-world usage patterns that may reveal:

  • Required composition patterns (e.g., Button needs ButtonText)
  • Prop combinations that work well together
  • Edge cases and accessibility considerations

4. Verify Dependencies

Use get_component_metadata to understand:

  • Peer dependencies that need to be installed
  • Other components that are used internally
  • TypeScript types that may need importing

Environment Configuration

The MCP server can operate in two modes:

GitHub Mode (Default)

Fetches components directly from the gluestack-ui GitHub repository.

bash
# Optional: Increase API rate limits
export GITHUB_TOKEN="your-token-here"

Local Mode

Uses a local clone of the gluestack-ui repository for offline access.

bash
# Point to your local clone
export GLUESTACK_PATH="/path/to/gluestack-ui"

Integration with Other Skills

Combine MCP tools with other gluestack skills:

  • gluestack-components: After getting source code, use component skill for implementation patterns
  • gluestack-theming: Use with Themed variant components for design token integration
  • gluestack-accessibility: Ensure retrieved components are implemented accessibly

Troubleshooting

Component Not Found

  • Verify the exact component name using list_components
  • Component names are case-sensitive
  • Some components may be grouped (e.g., FormControl components)

Rate Limiting

If using GitHub mode without a token:

  • Set GITHUB_TOKEN for increased limits
  • Or clone the repo locally and set GLUESTACK_PATH

Outdated Components

The MCP server fetches from the latest gluestack-ui repository. If you need a specific version:

  • Clone the specific version locally
  • Set GLUESTACK_PATH to your local clone

Frequently asked questions

What does the Gluestack Mcp Tools AI skill do?

Use when discovering, exploring, or retrieving gluestack-ui components via MCP tools. Provides access to component source code, variants, demos, and metadata.

Why use Gluestack Mcp Tools on TypingMind?

Because you install it once and use it with any model. Gluestack Mcp Tools 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 Gluestack Mcp Tools in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TheBushidoCollective/han/tree/main/plugins/frameworks/gluestack/skills/gluestack-mcp-tools. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gluestack Mcp Tools?

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 Gluestack Mcp Tools?

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

Is the Gluestack Mcp Tools AI skill free?

It is published on GitHub by TheBushidoCollective. 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 👇