Adeo Mozaic MCP
A

Adeo Mozaic MCP

The Mozaic MCP Server is a tool that provides query services for ADE0's Mozaic design system to AI assistants such as Claude. By indexing design tokens, component documentation, icons, and CSS utility classes, it enables AI to obtain design system information and generate code snippets.
2 points
7.2K

What is the Mozaic MCP Server?

The Mozaic MCP Server is a server specifically designed for AI assistants, which connects to ADEO's Mozaic design system. Through this server, AI assistants (such as Claude) can directly query various resources of the design system, including design specifications, UI components, icon libraries, and documentation. It's like equipping the AI assistant with a dedicated librarian for the design system, who can quickly find the information you need.

How to use the Mozaic MCP Server?

Using this server is very simple: First, you need to install and start the server. Then, configure the connection in an AI assistant that supports the MCP protocol (such as Claude Desktop). After the configuration is complete, you can directly ask the AI assistant questions related to the Mozaic design system, such as 'What are the attributes of the Mozaic button component?' or 'Give me the code for the main blue color tone.' The AI will obtain accurate information through the server and answer you.

Applicable scenarios

This service is particularly suitable for the following scenarios: 1) Front - end developers need to quickly consult design specifications when writing code; 2) Designers need to confirm the consistency of the design system; 3) New team members learn the Mozaic design system; 4) Verify compliance with design specifications during code review; 5) Quickly generate UI code snippets that comply with the design system.

Main features

Component query
Supports querying complete information of Vue and React components, including attributes, slots, events, and example code. You can browse all available components by category.
Design specification query
Provides queries for 586 design specifications, including colors, fonts, spacing, shadows, borders, etc., and supports filtering by category.
Icon search
Includes a search function for 1,473 icons, supports filtering by name, type (navigation, media, social, etc.) or size (16 - 64px), and provides SVG and React/Vue code.
CSS utility classes
Provides queries for 6 major categories of CSS utility classes, including the Flexy grid system, containers, margins, paddings, ratios, and scroll controls, with a total of more than 500 class names.
Full - text document search
Supports full - text search in 281 document pages, including design system documentation and Storybook usage guides.
Code generation
Automatically generates Vue or React component code based on design specifications to ensure that the code complies with the Mozaic design system standards.
Installation guide
Provides installation commands, import methods, and quick - start code for components to help developers quickly integrate components.
Advantages
One - stop query: Integrates all resources of the Mozaic design system, eliminating the need to switch between different documents
AI - friendly: Optimized specifically for AI assistants, providing a structured data interface
Real - time and accurate: Based on the latest Mozaic version (2.x), ensuring the timeliness of information
Multi - framework support: Supports both Vue 3 and React components
Ready - to - use code: The provided code examples can be directly copied and used
Limitations
Requires configuration: Server configuration is required in the AI assistant to use
Network - dependent: Needs to obtain the latest data from the GitHub repository
Learning curve: Requires understanding of basic MCP protocol concepts
Mozaic - only: Only supports ADEO's Mozaic design system and is not applicable to other design systems
Features in development: Some features (such as the installation guide) are still in the testing phase

How to use

Install the server
First, you need to install the Mozaic MCP Server. Use a package manager (such as pnpm) for installation.
Build the database
The server needs to build a local database to store design system data. This process will automatically obtain the latest data from the Mozaic GitHub repository.
Start the server
Start the MCP server, which will communicate with the AI assistant through standard input and output (stdio).
Configure the AI assistant
Configure the server connection in an AI assistant that supports MCP (such as Claude Desktop). Usually, you need to add server information to the configuration file.
Start querying
After the configuration is complete, you can directly ask the AI assistant questions related to the Mozaic design system.

Usage examples

Quickly find the button component
Developers need to know all available attributes and events of the Mozaic button component when writing the interface.
Confirm design specifications
Designers need to confirm whether a certain color value complies with the Mozaic design specifications.
Icon selection
Need to find suitable icons for the navigation menu.
Layout implementation
Need to implement a responsive layout using the Mozaic grid system.
Code generation
Need to quickly create a card component that complies with Mozaic specifications.

Frequently Asked Questions

What do I need to install to use this server?
Which AI assistants does this server support?
Is the data up - to - date? How to update it?
Is this server free?
Which design system versions are supported?
What should I do if I encounter a problem?
Will this server affect the performance of the AI assistant?
Can I extend this server to support other design systems?

Related resources

Official documentation
Complete project documentation, including architecture descriptions, API references, and usage guides
Online experience
Online demonstration and experience environment, allowing you to try the functions without installation
GitHub repository
Project source code, where you can view the code, submit issues, or participate in contributions
Mozaic design system
Official website of the ADEO Mozaic design system
Model Context Protocol
Official documentation and specifications of the MCP protocol
Claude Desktop
AI assistant desktop application supporting MCP

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
15.2K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.5K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.1K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.9K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
8.9K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
8.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
10.0K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
38.1K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
80.3K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.5K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.8K
4.5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
69.6K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.4K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.0K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
106.2K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase