Mesh Design System MCP Server
Provides containerized deployment of the MCP server using Docker for easy scaling and deployment options.
Uses FastAPI for the API endpoints that serve the MCP server functionality, including health checks, tool listings, and tool invocation.
Employs Pydantic models to structure the MCP request/response data, ensuring type validation for the API interactions.
Integrates with Storybook to provide direct links to component documentation, allowing AI assistants to reference visual examples of Mesh components.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MeshMCP - Mesh Design System MCP Server
A stdio-based Model Context Protocol (MCP) server that provides Claude Code (VS Code) access to the Mesh Design System components, design tokens, and prototyping tools.
Features
π¨ Component Discovery - List all Mesh Design System components
π Component Details - Get props, examples, and design guidance
π¨ Design Tokens - Access colors, typography, and spacing tokens
π Placeholder Data - Generate realistic insurance/healthcare test data
π Use Case Search - Find components for specific UI patterns
π» Code Generation - Generate React prototype code with Mesh components
β‘ Smart Caching - File-based caching with TTL for performance
Related MCP server: Vextra MCP Server
Quick Start
1. Install Dependencies
β οΈ Dependencies Fixed! See INSTALL.md for detailed installation instructions.
pip install -r requirements.txt
playwright install chromium2. Test the Server
python3 test_mcp.py3. Configure in VS Code
Add to ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:
{
"mcpServers": {
"mesh-design-system": {
"command": "python3",
"args": ["main.py"],
"cwd": "/Users/luke.ylias/Documents/GitHub/MeshMCP"
}
}
}Restart VS Code and start using the tools with Claude!
Available Tools
Tool | Description | Example |
| Lists all Mesh components | "List all Mesh components" |
| Get component props & examples | "Get details for Button component" |
| Retrieve design tokens | "Show me Mesh color tokens" |
| Generate test data | "Generate 5 member records" |
| Find components for use cases | "Components for a data table" |
| Generate React code | "Create a member signup form" |
Project Structure
MeshMCP/
βββ main.py # FastMCP server entry point
βββ requirements.txt # Python dependencies
βββ test_mcp.py # Test script
βββ SETUP.md # Detailed setup guide
βββ QUICK_START.md # Quick reference
βββ scrapers/
β βββ mesh_scraper.py # Web scraping with Playwright
βββ cache/
β βββ cache_manager.py # File-based caching
βββ generators/
β βββ data_generator.py # Placeholder data generation
βββ models/
βββ mcp_models.py # Pydantic modelsHow It Works
Claude Code (VS Code)
β stdio (JSON-RPC)
FastMCP Server (main.py)
β
βββββββββββββββββββββββββββββββ
β mesh_scraper.py (Playwright)β β Mesh Design System
β cache_manager.py (File) β β cache_data/
β data_generator.py (Faker) β β Test data
βββββββββββββββββββββββββββββββTroubleshooting
Server not connecting?
# Verify installation
python3 test_mcp.py
# Check MCP package
pip list | grep mcpCache issues?
# Clear cache (will regenerate)
rm -rf cache_data/Playwright errors?
# Reinstall browsers
playwright install --force chromiumDocumentation
QUICK_START.md - Installation & configuration in 3 steps
SETUP.md - Complete setup guide with troubleshooting
Tech Stack
MCP SDK - Model Context Protocol for Claude integration
Playwright - Web scraping for component data
Faker - Realistic Australian insurance data generation
Pydantic - Data validation
aiofiles - Async file operations for caching
License
See LICENSE file for details.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yoβ¦
The Figma MCP server brings Figma design context directly into your AI workflow.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseDqualityDmaintenanceA Model Context Protocol server that provides access to Magic UI components, allowing AI assistants and other MCP clients to discover and use UI components from the Magic UI design system.214MIT
- -licenseNot gradedqualityNot gradedmaintenanceA server based on Model Context Protocol that processes and parses design files (Vextra/Figma/Sketch/SVG), enabling AI assistants to access and manipulate design content.3-
- AlicenseAqualityDmaintenanceA Model Context Protocol server that exposes an airline design system as a queryable knowledge base, enabling AI to discover components, find components for use cases, and scaffold prototypes.321 npmMIT
- AlicenseNot gradedqualityDmaintenanceModel Context Protocol server that bridges design and development, giving AI assistants complete access to Figma for extraction, creation, debugging, and bidirectional token sync.12,081 npmMIT