Shopify Liquid MCP Server
Provides instant, offline access to complete Shopify Liquid documentation (198 docs covering tags, filters, and objects) for AI assistants to help with theme development and Liquid templating.
README
Shopify Liquid MCP Server
🚀 Fast, local, offline-first MCP server for Shopify Liquid documentation with 198 comprehensive docs including all tags, filters, and objects.
A specialized Model Context Protocol (MCP) server that provides instant access to complete Shopify Liquid documentation for AI assistants like Claude, Cursor, and other MCP-compatible tools.
🎯 Why This MCP Server?
vs. Official Shopify MCP
While Shopify provides an official MCP server that covers all Shopify APIs, this server is specifically optimized for Liquid template development:
| Feature | Official Shopify MCP | This (Liquid MCP) |
|---|---|---|
| Focus | All Shopify APIs (Admin, Storefront, Functions, etc.) | Liquid templating only |
| Storage | Remote (queries shopify.dev) | Local (no network needed) |
| Speed | Network-dependent | Instant (<1ms) |
| Offline | ❌ Requires internet | ✅ Fully offline |
| Customization | Fixed documentation | Add your own docs |
| Coverage | General API docs | 198 Liquid-specific docs |
| Runtime | Node.js | Python |
Use Cases
Use Official Shopify MCP for:
- Admin API/GraphQL development
- App development with Shopify APIs
- Functions and POS extensions
- Real-time schema validation
Use This Liquid MCP for:
- Theme development with Liquid
- Liquid template debugging
- Offline development
- Faster Liquid reference lookups
- Project-specific Liquid snippets
Use Both! They complement each other perfectly - official MCP for APIs, this for Liquid.
✨ Features
- 🚀 Lightning Fast - Local SQLite FTS5 search (<1ms response time)
- 📚 Complete Coverage - 30 tags, 101 filters, 67 objects (198 total docs)
- 🔌 Offline First - No network requests, works anywhere
- 🐳 Docker Ready - One command deployment
- 🎨 IDE Integration - Works with VS Code, Cursor, Claude Desktop, Zed
- 🔧 Customizable - Add your own project-specific Liquid docs
- 📖 Rich Documentation - Full syntax, parameters, examples for everything
- 🔍 Smart Search - Full-text search with snippet highlighting
📦 Installation
Option 1: Using pip (Recommended)
pip install git+https://github.com/florinel-chis/shopify-liquid-mcp.git
Option 2: Using Docker
# Pull the image
docker pull florinel-chis/shopify-liquid-mcp:latest
# Or build locally
docker build -t shopify-liquid-mcp .
docker run -it shopify-liquid-mcp
Option 3: Using docker-compose
docker-compose up -d
Option 4: From Source
git clone https://github.com/florinel-chis/shopify-liquid-mcp.git
cd shopify-liquid-mcp
pip install -e .
🎮 Usage
With VS Code
Using Docker
Create or edit .vscode/settings.json:
{
"mcp.servers": {
"shopify-liquid": {
"type": "docker",
"image": "shopify-liquid-mcp:latest",
"transport": "stdio"
}
}
}
Using Local Installation
Create .mcp.json in your project root:
{
"mcpServers": {
"shopify-liquid": {
"type": "stdio",
"command": "shopify-liquid-mcp"
}
}
}
Or add to VS Code settings:
{
"mcp.servers": {
"shopify-liquid": {
"command": "shopify-liquid-mcp",
"args": [],
"transport": "stdio"
}
}
}
With Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Using Docker
{
"mcpServers": {
"shopify-liquid": {
"type": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "shopify-liquid-mcp:latest"]
}
}
}
Using Local Installation
{
"mcpServers": {
"shopify-liquid": {
"command": "shopify-liquid-mcp"
}
}
}
With Cursor
Add to Cursor's MCP configuration (Settings > Features > MCP Servers):
{
"mcpServers": {
"shopify-liquid": {
"command": "shopify-liquid-mcp"
}
}
}
Or with Docker:
{
"mcpServers": {
"shopify-liquid": {
"command": "docker",
"args": ["run", "-i", "--rm", "shopify-liquid-mcp:latest"]
}
}
}
With Zed Editor
Create .zed/settings.json:
{
"context_servers": {
"shopify-liquid": {
"command": "shopify-liquid-mcp"
}
}
}
With Continue.dev
Edit ~/.continue/config.json:
{
"mcpServers": [
{
"name": "shopify-liquid",
"command": "shopify-liquid-mcp"
}
]
}
🛠️ Available Tools
Once configured, your AI assistant has access to 7 specialized tools:
1. search_liquid_docs(queries: List[str])
Full-text search across all Shopify Liquid documentation.
Example:
AI: I'll search for "for loop" in the documentation...
2. get_liquid_tag(tag_name: str)
Get complete documentation for a specific tag.
Example:
AI: Let me get the documentation for the 'for' tag...
3. get_liquid_filter(filter_name: str)
Get complete documentation for a specific filter.
Example:
AI: I'll look up the 'upcase' filter documentation...
4. get_liquid_object(object_name: str)
Get complete documentation for a specific object.
Example:
AI: Let me check the 'product' object properties...
5. list_liquid_tags()
List all 30 available tags organized by category.
6. list_liquid_filters()
List all 101 available filters organized by category.
7. list_liquid_objects()
List all 67 available objects organized by category.
💬 Example Queries
Try asking your AI assistant:
Getting Documentation:
- "Show me documentation for the for loop tag"
- "How does the money filter work in Liquid?"
- "What properties are available on the product object?"
Searching:
- "Search for documentation about cart functionality"
- "Find all filters related to dates"
- "What objects can I use for collections?"
Listing:
- "List all Shopify Liquid tags"
- "Show me all available string filters"
- "What iteration tags are available?"
Building:
- "Help me display products in a grid"
- "How do I format dates in Liquid?"
- "Show me how to work with the cart"
📊 Documentation Coverage
Complete Reference
-
30 Liquid Tags
- Control flow:
if,unless,case,else - Iteration:
for,break,continue,cycle,tablerow,paginate - Variables:
assign,capture,increment,decrement,echo - Theme:
layout,section,sections,render,include,content_for - HTML/Assets:
form,style,stylesheet,javascript - Syntax:
comment,raw,liquid,doc
- Control flow:
-
101 Liquid Filters
- String (24):
upcase,downcase,capitalize,append,prepend, etc. - Array (13):
join,sort,reverse,map,where,size, etc. - Math (11):
plus,minus,times,divided_by,modulo, etc. - Money (4):
money,money_with_currency, etc. - Image (5):
image_url,image_tag, etc. - Color (9):
color_darken,color_lighten, etc. - And more...
- String (24):
-
67 Liquid Objects
- Store:
shop,settings,theme,brand - Products:
product,variant,collection,collections - Cart:
cart,line_item,checkout - Customer:
customer,address,company - Content:
page,blog,article,comment - Media:
image,video,media,model - And more...
- Store:
🐳 Docker Usage
Quick Start
# Build the image
docker build -t shopify-liquid-mcp .
# Run the server
docker run -it --rm shopify-liquid-mcp
# Run with persistent data
docker run -it --rm -v mcp-data:/data shopify-liquid-mcp
Using docker-compose
# Start the server
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the server
docker-compose down
# Shell access
docker-compose exec shopify-liquid-mcp bash
Custom Documentation
Add your project-specific Liquid docs:
# Create custom docs directory
mkdir custom-docs
# Add your .md files
cp my-snippets.md custom-docs/
# Mount in docker-compose.yml
volumes:
- ./custom-docs:/docs/custom:ro
🔧 Development
Running Tests
# Run all tests
pytest
# Run specific test
pytest tests/test_ingest.py
# Run with coverage
pytest --cov=shopify_liquid_mcp
Manual Testing
# Test the server
python test_server.py
# Test indexing
python -m shopify_liquid_mcp.ingest
# Check database
sqlite3 ~/.mcp/shopify-liquid-docs/database.db "SELECT COUNT(*) FROM liquid_docs;"
Reindexing Documentation
# Force reindex
python -m shopify_liquid_mcp.ingest --force
# Custom database location
SHOPIFY_LIQUID_DB_PATH=/custom/path/db.sqlite python -m shopify_liquid_mcp.ingest
📖 Documentation
🤝 Contributing
Contributions welcome! Please read our Contributing Guide.
Quick Start
# Fork and clone
git clone https://github.com/florinel-chis/shopify-liquid-mcp.git
cd shopify-liquid-mcp
# Create virtual environment
python -m venv venv
source venv/bin/activate # or `venv\Scripts\activate` on Windows
# Install for development
pip install -e ".[dev]"
# Run tests
pytest
# Make changes and submit PR
📜 License
MIT License - see LICENSE file for details.
🙏 Acknowledgments
- Inspired by Gemini API Docs MCP
- Built with FastMCP
- Documentation from Shopify Liquid API
- MCP Protocol by Anthropic
🔗 Related Projects
- Official Shopify Dev MCP - For Shopify API development
- FastMCP - MCP server framework
- Model Context Protocol - MCP specification
📞 Support
- 🐛 Issues
- 💬 Discussions
⭐ Star History
Made with ❤️ for the Shopify theme development community
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.