SommelierX Wine Pairing MCP
Wine pairing intelligence for AI assistants. 7 MCP tools for sommelier-grade wine recommendations: pair wines with meals, ingredients, or recipe URLs, reverse pairing, group dinner planning, and search. Powered by a proprietary Wine DNA algorithm with 600+ wine archetypes. Supports API key and x402 (USDC on Base) autonomous agent payments.
README
@sommelierx/mcp-server
Wine pairing intelligence for AI assistants. Connect Claude, Cursor, Windsurf, or any MCP-compatible client to a sommelier-grade pairing algorithm that matches wines to your ingredients, dishes, and recipes.
Quick Start
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"sommelierx": {
"command": "npx",
"args": ["@sommelierx/mcp-server"]
}
}
}
That is it. Ask Claude "What wine goes with grilled salmon?" and it will use SommelierX to answer.
With a Pro API key
For recipe extraction, group pairing, and score breakdowns:
{
"mcpServers": {
"sommelierx": {
"command": "npx",
"args": ["@sommelierx/mcp-server"],
"env": {
"SOMMELIERX_API_KEY": "sk_live_your_key_here"
}
}
}
}
Cursor / Windsurf / Other MCP Clients
The same configuration works. Add the command and args to your client's MCP settings.
Available Tools
| Tool | What it does | Tier |
|---|---|---|
pair_wine_with_ingredients |
Find wines for a list of ingredients (e.g. "salmon, lemon, dill") | Free |
pair_wine_with_meal |
Find wines for a dish name (e.g. "risotto ai funghi") | Free |
find_meals_for_wine |
Find dishes that pair with a wine style (e.g. "Barolo") | Free |
search_ingredients |
Search the ingredient database | Free |
search_meals |
Search the meal database | Free |
pair_wine_with_recipe_url |
Extract ingredients from a recipe URL and pair wines | Pro |
group_pairing |
Find the best wine across multiple dishes (e.g. 3-course dinner) | Pro |
Authentication
SommelierX supports two authentication methods. You can use either one -- no need to configure both.
Option 1: API Key (subscription)
Set the SOMMELIERX_API_KEY environment variable in your MCP client config. The key format is sk_live_.... You get a monthly call allowance based on your tier (Free / Pro / Enterprise).
{
"mcpServers": {
"sommelierx": {
"command": "npx",
"args": ["@sommelierx/mcp-server"],
"env": {
"SOMMELIERX_API_KEY": "sk_live_your_key_here"
}
}
}
}
Get your API key at api.sommelierx.com.
Option 2: x402 Payment (pay per call)
No API key needed. Your AI agent pays per call using USDC on the Base network via the Coinbase x402 protocol. When a request lacks an API key, the server returns a 402 Payment Required response with a payment payload. x402-compatible agents handle this automatically.
This is ideal for:
- AI agents that manage their own wallet
- Pay-as-you-go usage without a subscription
- Agent-to-agent commerce (no human in the loop)
Pricing (per call)
| Tool | Price | Tier |
|---|---|---|
pair_wine_with_meal |
$0.01 | Free |
find_meals_for_wine |
$0.01 | Free |
search_ingredients |
$0.005 | Free |
search_meals |
$0.005 | Free |
pair_wine_with_ingredients |
$0.02 | Pro |
pair_wine_with_recipe_url |
$0.02 | Pro |
group_pairing |
$0.03 | Pro |
With an API key, calls are deducted from your tier allowance. With x402, each call is charged at the listed price.
Example Conversations
Basic pairing:
"What wine pairs well with salmon, asparagus, and hollandaise sauce?"
Reverse pairing:
"I have a bottle of Barolo. What should I cook?"
Recipe URL:
"What wine goes with this recipe? https://www.allrecipes.com/recipe/..."
Dinner party:
"I'm planning a 3-course dinner: Caesar salad, rack of lamb, and chocolate mousse. What single wine works for all courses?"
How It Works
- You ask your AI assistant a wine question
- The assistant calls the appropriate SommelierX tool
- The MCP server translates your input into structured API calls
- SommelierX's pairing algorithm (17 food DNA dimensions x 19 wine DNA dimensions) calculates matches
- You get scored wine recommendations based on real sommelier expertise
Ingredient Resolution
When you use pair_wine_with_ingredients, the server automatically resolves natural language ingredient names to database entries. The AI assistant does not need to know database IDs -- it passes ingredient names directly.
Configuration
| Environment Variable | Required | Default | Description |
|---|---|---|---|
SOMMELIERX_API_KEY |
No | -- | API key for Pro/Enterprise access. Without a key, free tier (50 calls/day). |
SOMMELIERX_API_URL |
No | https://api.sommelierx.com |
API base URL. |
SOMMELIERX_LANGUAGE |
No | en |
Default language for results (en, nl, fr, de, es, it). |
API Tiers
| Tier | Daily Limit | Per-Minute Limit | Features |
|---|---|---|---|
| Free | 50 calls | 2/min | Basic pairing, search, ingredient/meal lookup |
| Pro ($49/mo) | 500 calls | 20/min | + Recipe URL extraction, group pairing, score breakdowns |
| Enterprise | 10,000 calls | 100/min | + Custom limits, SLA |
Get your API key at api.sommelierx.com
API Documentation
Full API documentation is available at docs.sommelierx.com.
The OpenAPI specification is served at https://api.sommelierx.com/api/v1/openapi.json.
Development
npm install
npm run build
npm run dev # development mode with hot reload
npm run typecheck # type checking without emit
Requirements
- Node.js >= 18.0.0
License
MIT
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.