mcp-server-gelato
Gelato
Documentation
Gelato MCP Server
An MCP (Model Context Protocol) server for integrating with Gelato's print-on-demand API. This server provides tools and resources to search orders, retrieve order details, and explore product catalogs.
Features
๐ง Tools
- search_orders: Advanced order search with multiple filters (status, country, date range, etc.)
- get_order_summary: Retrieve specific order details
- search_products: Search products in catalogs with filtering capabilities
- get_product: Get detailed information about a specific product
- get_product_prices: Get pricing information for products
- check_stock_availability: Check stock availability across regions
- list_shipment_methods: Get available shipment methods
๐ Resources
- orders://{order_id}: Get detailed order information
- orders://recent: Get the 10 most recent orders
- orders://drafts: Get all draft orders
- catalogs://list: List all available product catalogs
- catalogs://{catalog_uid}: Get detailed catalog information
- catalogs://summary: Quick overview of all catalogs
Prerequisites
- Python 3.13+
- Gelato API key (get one from Gelato API Portal)
Installation
Quick Install with Claude Desktop
The easiest way to add this server to Claude Desktop:
claude mcp add gelato --env GELATO_API_KEY="your_gelato_api_key_here" -- uvx mcp-server-gelatoReplace `your_gelato_api_key_here` with your actual Gelato API key from the Gelato API Portal.
Alternative: You can install without the API key and configure it later:
claude mcp add gelato -- uvx mcp-server-gelatoThen use the `configure_gelato` tool within Claude to set up your API key.
Manual Installation
Option 1: Install from PyPI (Recommended)
# Install the package
uv install mcp-server-gelato
# or
pip install mcp-server-gelato
# Run the server
GELATO_API_KEY="your_api_key_here" uvx mcp-server-gelato
# Or install as a tool
uv tool install mcp-server-gelato
GELATO_API_KEY="your_api_key_here" mcp-server-gelatoOption 2: Install from GitHub
# Install directly from GitHub
uvx --from git+https://github.com/madzarmaksim/mcp-server-gelato mcp-server-gelato
# Or use uv tool install
uv tool install git+https://github.com/madzarmaksim/mcp-server-gelatoOption 3: Local Development
1. Clone this repository:
git clone https://github.com/madzarmaksim/mcp-server-gelato.git
cd mcp-server-gelato2. Install dependencies:
uv install
# or
pip install -e .3. Set up your API key:
cp .env.example .env
# Edit .env and add your GELATO_API_KEYConfiguration
Create a `.env` file in the project root with your Gelato API key:
GELATO_API_KEY=your_gelato_api_key_here
# Optional configuration
# GELATO_BASE_URL=https://order.gelatoapis.com
# GELATO_PRODUCT_URL=https://product.gelatoapis.com
# TIMEOUT=30
# MAX_RETRIES=3
# DEBUG=falseUsage
Running the Server
After installation via uvx:
# Run the server directly
mcp-server-gelato
# Or with environment variables
GELATO_API_KEY=your_key_here mcp-server-gelatoLocal development:
# Direct execution
python main.py
# Development mode with inspector
uv run mcp dev main.py
# Install in Claude Desktop from local directory
uv run mcp install . --name "Gelato API"Using the Tools and Resources
Search Orders
# Search for draft orders
search_orders(order_types=["draft"])
# Search US orders from last month
search_orders(
countries=["US"],
start_date="2024-01-01T00:00:00Z",
end_date="2024-01-31T23:59:59Z"
)
# Search by customer name
search_orders(search_text="John Smith", limit=10)Get Order Details
Use the resource URI format to load order context:
orders://37365096-6628-4538-a9c2-fbf9892deb85Or use the tool:
get_order_summary(order_id="37365096-6628-4538-a9c2-fbf9892deb85")Explore Product Catalogs
catalogs://list # List all catalogs
catalogs://posters # Get poster catalog details
catalogs://summary # Quick overviewAvailable Search Filters
The `search_orders` tool supports extensive filtering:
- order_types: `["order", "draft"]` - Filter by order type
- countries: `["US", "DE", "CA"]` - Filter by shipping country
- currencies: `["USD", "EUR", "GBP"]` - Filter by currency
- financial_statuses: Payment statuses (`"draft"`, `"paid"`, `"canceled"`, etc.)
- fulfillment_statuses: Fulfillment statuses (`"created"`, `"printed"`, `"shipped"`, etc.)
- search_text: Search in customer names and order reference IDs
- start_date/end_date: Date range filtering (ISO 8601 format)
- channels: `["api", "shopify", "etsy", "ui"]` - Filter by order channel
- limit/offset: Pagination control (max 100 results per request)
Key Design Features
- Type Safety: Full Pydantic models for all API interactions
- Error Handling: Comprehensive error handling with custom exceptions
- Async Support: All API calls are async for better performance
- Resource vs Tools: Clear separation between data exposure (resources) and operations (tools)
- Extensible: Easy to add new endpoints by following established patterns
Error Handling
The server includes robust error handling for common scenarios:
- Authentication errors: Invalid or missing API keys
- Rate limiting: Automatic retry with exponential backoff
- Network errors: Timeout and connection error handling
- API errors: Proper handling of Gelato API error responses
- Validation errors: Request/response data validation
Troubleshooting
"Failed to reconnect to gelato" Error
This error occurs when the server starts without a valid `GELATO_API_KEY`. Here are the solutions:
For Claude Desktop Installation:
# Install with API key (recommended)
claude mcp add gelato --env GELATO_API_KEY="your_actual_api_key" -- uvx mcp-server-gelato
# Or install without API key and configure later
claude mcp add gelato -- uvx mcp-server-gelato
# Then use the configure_gelato tool in ClaudeFor Local Development:
# Using PyPI package
GELATO_API_KEY="your_api_key_here" uvx mcp-server-gelato
# Or using local code
export GELATO_API_KEY=your_api_key_here
python main.py
# Or create .env file for local development
echo "GELATO_API_KEY=your_api_key_here" > .env
python main.pyGetting Your API Key
1. Visit the Gelato API Portal
2. Sign up or log in to your account
3. Generate an API key from your dashboard
4. Use the key in the installation command or environment variable
Common Issues
- Invalid API Key: Double-check your API key is correct and active
- Network Issues: Ensure internet connectivity and no firewall blocking
- Permission Issues: Make sure your API key has the necessary permissions
Development
Adding New Features
1. New Tools: Add to `src/tools/` and register in server
2. New Resources: Add to `src/resources/` and register in server
3. New Models: Add to `src/models/` with proper Pydantic validation
4. New API Endpoints: Extend `GelatoClient` in `src/client/`
Testing
# Test connection with your API key
python -c "
import asyncio
from src.config import get_settings
from src.client.gelato_client import GelatoClient
async def test():
settings = get_settings()
async with GelatoClient(settings.gelato_api_key, settings) as client:
catalogs = await client.list_catalogs()
print(f'Found {len(catalogs)} catalogs')
asyncio.run(test())
"Troubleshooting
Common Issues
1. API Key Error: Make sure `GELATO_API_KEY` is set correctly in your environment
2. Connection Timeout: Check your network connection and increase timeout in config
3. Rate Limiting: The server automatically retries with backoff, but you may need to slow down requests
Debug Mode
Enable debug logging:
DEBUG=true python main.pyContributing
1. Follow the existing code structure and patterns
2. Add proper error handling for new endpoints
3. Include Pydantic models for data validation
4. Document new features in this README
License
This project is licensed under the MIT License.
Support
For Gelato API issues, visit the Gelato Help Center.
For MCP-related issues, check the MCP documentation.
Frequently asked questions
What is mcp-server-gelato?
mcp-server-gelato is Gelato
How do I install mcp-server-gelato?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-server-gelato open source?
Yes โ it is hosted on GitHub at https://github.com/madzarm/mcp-server-gelato.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP