About recipe-commerce-mcp
recipe-commerce-mcp extracts structured ingredients and equipment from cooking transcripts or YouTube URLs, then matches them to purchasable products and affiliate programs. It is for recipe publishers and commerce workflows building shoppable lists.
Key features
- 01Recipe ingredient extraction
- 02Product and affiliate matching
- 03Ranked affiliate shopping lists
- 04Equipment identification
- 05Price and commission details
Use cases
- 01Create shopping lists from cooking videos
- 02Match recipe ingredients to affiliate products
- 03Prioritize products by revenue potential
MCP support
It exposes tools to MCP clients for extracting recipe data, matching ingredients to products, and suggesting affiliate products.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y recipe-commerce-mcpOPENAI_API_KEYSecretOpenAI API key for GPT-4o-mini product extraction (required)MCP_API_KEYSSecretComma-separated paid API keys for unlimited calls (optional — omit for free tier: 200 calls/day)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
3Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| api_key | string | No | Optional API key for paid access beyond the free tier |
| recipe_id | string | No | Optional recipe identifier for caching. Auto-derived from content if omitted. |
| transcript | string | Yes | Raw transcript text OR a YouTube URL (e.g. https://youtube.com/watch?v=...) |
Details
From the project READMERecipe Commerce Intelligence MCP
Turn recipes into affiliate revenue. Extract every branded ingredient and kitchen tool from any recipe, match each to Amazon Associates, ShareASale, or Awin, and generate a shoppable ingredient list in seconds. F1=100% on eval suite. Free tier: 200 calls/day.
⭐ If this saves you time, please star the repo — it helps other developers find it.
Live endpoint:
https://recipe-commerce-mcp.sincetoday.workers.dev/mcp· See examples
Extract recipes and ingredients from cooking video transcripts, match to purchasable products, and build affiliate shopping lists. Built on x402, the open payment standard backed by Shopify, Google, Microsoft, Visa, and the Linux Foundation.
Tools
| Tool | Description |
|---|---|
extract_recipe_ingredients | Extract structured recipe data from a cooking video transcript or YouTube URL |
match_ingredients_to_products | Match ingredients to purchasable products with affiliate program details |
suggest_affiliate_products | Generate a ranked affiliate shopping list scored by revenue potential |
Connect in Claude Code — No Install Required
Add to your claude_desktop_config.json or use /add-mcp in Claude Code. Free tier: 200 calls/day, no API key needed:
{
"mcpServers": {
"recipe-commerce": {
"url": "https://recipe-commerce-mcp.sincetoday.workers.dev/mcp"
}
}
}
Quick Start
# Install
npm install recipe-commerce-mcp
# Configure
cp .env.example .env
# Edit .env: set OPENAI_API_KEY
# Run (stdio MCP server)
npx recipe-commerce-mcp
MCP Client Config
{
"mcpServers": {
"recipe-commerce": {
"command": "npx",
"args": ["recipe-commerce-mcp"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}
Tool Reference
extract_recipe_ingredients
{
"transcript": "Cooking video transcript or YouTube URL",
"recipe_id": "optional-cache-key",
"api_key": "optional-paid-key"
}
Returns:
{
"result": {
"recipeName": "Beef Bourguignon",
"ingredients": [
{ "name": "beef chuck", "quantity": "2", "unit": "lbs", "category": "meat", "is_optional": false }
],
"equipment": [
{ "name": "Le Creuset Dutch oven 5.5qt", "category": "cookware", "requiredForRecipe": true }
],
"techniques": ["braising", "searing"],
"cuisineType": "French",
"difficulty": "medium"
},
"_meta": { "processing_time_ms": 1950, "ai_cost_usd": 0.0024, "cache_hit": false, "recipe_id": "..." }
}
match_ingredients_to_products
{
"ingredients": [{ "name": "beef chuck", "quantity": "2", "unit": "lbs" }],
"recipe_id": "optional-uses-cached-ingredients",
"api_key": "optional"
}
Returns affiliate program details (Amazon Associates, ShareASale, Awin), price range, commission rate (2–10%), brand? (extracted brand name for branded ingredients, e.g. "Maldon" for "Maldon salt"), estimatedCommission (USD estimate based on price × commission rate), and substitution alternatives.
suggest_affiliate_products
{
"recipe_name": "Beef Bourguignon",
"ingredients": [...],
"api_key": "optional"
}
Returns ingredients and equipment ranked by affiliate revenue score. Equipment scores highest (10% commission via Amazon Associates).
Example Output
Real extraction from a Serious Eats beef bourguignon recipe (live eval avg: F1=93%, 98/100 score, $0.000370/call, 2608ms):
{
"recipe_id": "serious-eats-beef-bourguignon",
"ingredients": [
{
"name": "Dutch oven (5.5 qt)",
"brand": "Le Creuset",
"category": "equipment",
"is_optional": false,
"affiliate_revenue_score": 0.92,
"estimatedCommission": 8.50,
"amazon_search_terms": ["dutch oven 5.5 quart", "Le Creuset 5.5 qt"]
},
{
"name": "Maldon sea salt",
"brand": "Maldon",
"category": "ingredient",
"is_optional": false,
"affiliate_revenue_score": 0.18,
"estimatedCommission": 0.42
},
{
"name": "beef chuck",
"brand": null,
"category": "ingredient",
"is_optional": false,
"affiliate_revenue_score": 0.12,
"estimatedCommission": null,
"amazon_search_terms": null
}
]
}
See /examples endpoint for full output with value narrative: https://recipe-commerce-mcp.sincetoday.workers.dev/examples
Pricing
- Free tier: 200 calls/day per agent (no API key required)
- Paid: $0.01/call — set
MCP_API_KEYSwith valid keys
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
OPENAI_API_KEY | Yes | — | OpenAI API key |
AGENT_ID | No | anonymous | Agent identifier for rate limiting |
MCP_API_KEYS | No | — | Comma-separated paid API keys |
CACHE_DIR | No | ./data/cache.db | SQLite cache path |
PAYMENT_ENABLED | No | false | Set true to enforce limits |
Development
npm install
npm run typecheck # Zero type errors
npm test # All tests pass
npm run build # Compile to dist/
License
MIT — Since Today Studio
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.